TradePilot Agent Commerce

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states 'no external research or outbound actions' and 'returns a draft for human review,' yet the annotations declare openWorldHint=true and destructiveHint=true. This is a direct contradiction: the description claims a closed, non-destructive generation behavior while the annotations warn of open-world and destructive characteristics. Score 1 per the contradiction rule.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the core action: create an about page from supplied content. Each sentence adds meaningful information, though 'buyer-supplied information only' partially repeats the earlier 'supplied... only' constraint. Minor redundancy, but otherwise well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With five parameters, a nested input object, no output schema, and no parameter documentation, the description should explain how to provide the source material, what the returned draft looks like, and what payment authorization entails. It only says a draft is returned and payment requires wallet authorization, which is insufficient for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain any of the five top-level parameters or the nested input fields. It alludes to buyer-supplied content and wallet authorization, but it does not connect those concepts to brief, audience, source_text, payment_signature, idempotency_key, or result_expires. For a low-coverage schema, the description should have compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: create a business about page. It also specifies the source scope — supplied history, mission, people, and operating principles only — which clearly distinguishes it from research-based siblings like market_report_from_sources and from similar copy tools like homepage_copy or service_page_copy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: use buyer-supplied information only, no external research, and expect a draft for human review. It does not explicitly name an alternative tool to use when external research is needed, but the constraints are clear enough to route an agent appropriately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds meaningful behavioral context beyond the annotations: buyer-supplied information only, no outbound calls, a human-review draft as output, a 0.25 USD cost, and explicit wallet authorization. This gives the agent important side-effect and payment context that the schema and annotation booleans alone do not convey. No contradiction with the annotations is present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences with the core function front-loaded, followed by scope constraints, return type, and pricing/payment. No filler or redundant restatement of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the main purpose, data-source constraints, return type, and payment side effect, which is helpful given no output schema. However, it leaves a notable gap by not explaining how the required nested `input` fields should be filled or what the optional expense/signature parameters mean, so the agent must infer parameter semantics from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description needed to explain the parameters, but it never names or maps `input.brief`, `input.source_text`, `audience`, or the signature/idempotency fields. It only mentions high-level account-fact categories, which hints at content but not at how to populate the nested `input` object.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Build an account plan from supplied account facts,' and lists the components (hypotheses, stakeholders, objectives, next actions). This is clear and distinguishes the tool from generic plan tools, though it does not explicitly contrast a sibling tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context for use: the tool consumes buyer-supplied account facts only, performs no external research or outbound actions, and returns a draft for human review. It does not explicitly name alternatives or state when not to use it, so exclusions remain implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true. The description adds important behavioral context: it does not perform external research, uses only buyer-supplied info, returns a draft for human review, and requires payment with explicit wallet authorization. This goes beyond the annotations and clarifies the destructive/payment nature. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose and key constraints. It includes pricing and payment authorization, which are essential. It's concise and each sentence adds value, though the payment details could arguably be in annotations or structured fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, constraints, and payment requirement, but with no output schema and 0% parameter coverage, it leaves the agent without guidance on what the draft output looks like or how to fill the required parameters. The description is adequate for basic selection but incomplete for correct invocation without schema inspection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for explaining parameters. The description mentions 'buyer-supplied information' and 'source_text' implicitly, but it doesn't explain the key parameters: brief, source_text, audience, result_expires, idempotency_key, result_signature, payment_signature. The description does not map to the schema fields, leaving the agent to infer what 'brief' and 'source_text' mean. This is a significant gap given 0% coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a research checklist and source plan, and explicitly notes it does not perform research. It distinguishes itself from research-performing tools by stating 'do not claim the research has been performed' and 'no external research or outbound actions.' However, it doesn't explicitly name a sibling alternative, so it's clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: it uses buyer-supplied information only, no external research, and returns a draft for human review. This implies when to use it (when a research plan is needed, not actual research) and when not to use it (when research execution is needed). It doesn't explicitly name alternatives, but the constraints are explicit enough to guide selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the annotations. The 'openWorldHint' is true, but the description states 'no external research or outbound actions,' implying it does not interact with the outside world. This is a clear contradiction, so according to the rubric the score must be 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with no filler. It front-loads the core extraction purpose and then clarifies constraints and output. The inclusion of price and payment authorization is necessary information for an agent to decide on invocation, and it is presented economically.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the scope, input source, and output nature, and mentions payment requirements. However, it omits any reference to the specific parameters, and the contradiction with annotations undermines trust. While the schema provides parameter details, the contradictory behavior statement creates a serious gap in the overall context an agent needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides no explanation of the parameters (input object with brief and source_text, result_expires, idempotency_key, signatures, etc.). The description only mentions 'supplied notes' and 'buyer-supplied information,' which is vague and does not help an agent understand how to fill the required fields. With zero coverage, the description fails to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action of extracting only evidenced actions, owners, due dates, and unresolved assignments from supplied notes. It uses a specific verb and resource, and the focus on 'evidenced actions' distinguishes it from other extraction tools like entity_extraction or requirements_extraction, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when you need action items from notes) but does not explicitly state when to use it versus alternatives or when not to use it. There is no mention of sibling tools or exclusions, so an agent must infer the appropriate context from the purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description's 'no external research or outbound actions' and 'Returns a draft for human review' directly contradict the annotations openWorldHint=true, readOnlyHint=false, and destructiveHint=true. This is a clear annotation contradiction, warranting a score of 1 regardless of any other useful behavioral details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is about 60 words and front-loaded with the core action, followed by constraints, pricing, and payment authorization—all necessary for safe invocation. There is no filler or redundant restatement, making it appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, a nested input object, no output schema, and 0% schema coverage, the description fails to clarify parameter semantics and contradicts the annotations. The agent lacks essential information about expected inputs and behavioral side effects, making the definition incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only mentions 'buyer-supplied information' without explaining the input object's brief/audience/source_text semantics or the roles of payment_signature, idempotency_key, and result_expires. This is a critical gap for a tool with 5 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Produce') and resource ('distinct advertising concepts') with the output components (headline, body, CTA, rationale) listed, which distinguishes it from generic copy tools. It does not explicitly differentiate from close siblings like headline_variants or social_posts, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context—buyer-supplied information only, no external research or outbound actions—which implies a boundary, but it does not explicitly say when to use this tool versus alternatives. No sibling tools are mentioned, making selection guidance minimal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description says 'no external research or outbound actions' while annotations set openWorldHint=true, which typically indicates the tool may interact with the external world. This is a direct contradiction. While it adds useful context about payment and review, the contradiction warrants a score of 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero filler. The first sentence states the core function, the second scopes inputs and outputs, the third states price and authorization. All content earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core behavior and payment requirement, but given the tool has five parameters, a nested input object, no output schema, and a contradictory annotation, it's incomplete. The agent cannot infer correct values for idempotency_key, result_expires, or the structure of the 'brief' field. The openWorldHint contradiction further reduces trust.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters but doesn't. It mentions 'audience' as an output component but not as an input parameter; it doesn't explain 'brief', 'source_text', 'result_expires', 'idempotency_key', 'result_signature', or 'payment_signature' semantics. The only hint is that payment requires wallet authorization, which loosely relates to payment_signature, but that's insufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb 'Produce' and resource 'writing brief' with explicit components (audience, thesis, outline, evidence, acceptance criteria), clearly distinguishing it from blog_draft which would produce the article itself. However, it doesn't explicitly name sibling alternatives like seo_content_brief, so it's not a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes clear context: uses buyer-supplied information only, no external research, returns draft for human review, and requires explicit wallet authorization. This implies when to use it (for planning from existing info) but doesn't explicitly contrast with sibling tools or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds valuable behavioral context beyond the annotations: it explicitly states the tool uses only buyer-supplied facts (no external research), returns a draft for human review, and requires explicit wallet authorization for payment. The annotations already declare destructiveHint=true (likely indicating side effects like charging), and the description's payment note aligns with that. It doesn't contradict the annotations. It could have elaborated on the destructive hint, but overall it provides meaningful operational transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with the primary purpose front-loaded in the first sentence, followed by usage constraints, output nature, and pricing. Each sentence earns its place—no fluff. It could be slightly more structured (e.g., separating pricing into a distinct block), but the information flow is logical and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (nested input object with three subfields, plus four other parameters, no output schema), the description is incomplete. It fails to explain how to populate input.brief, input.audience, and input.source_text, nor does it describe the purpose of result_expires, idempotency_key, result_signature, or payment_signature. The only operational detail is the price and payment authorization. An agent lacks guidance on making a correct call, especially around payment and result retrieval, so the description is insufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the lack of parameter information. However, it does not explain any of the five parameters (input, result_expires, idempotency_key, result_signature, payment_signature). It only indirectly references the input via 'supplied facts' and mentions payment, but does not clarify the purpose of parameters like idempotency_key or result_signature. An agent would be left guessing how to construct the request correctly, especially the payment and result-handling fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Write'), a resource ('a complete article'), and explicit constraints ('based only on supplied facts', 'with headings and an actionable conclusion'). This distinguishes it from sibling tools like blog_brief (which likely produces a brief, not a full article) and ad_copy or social_posts. The purpose is unambiguous and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies when to use this tool: when the buyer supplies facts and no external research is desired ('Uses buyer-supplied information only; no external research or outbound actions'). It also clarifies it returns a draft for human review. However, it does not explicitly name alternative tools or state when not to use it, so it lacks explicit exclusion criteria. The usage context is clear enough for an agent to decide, but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint=false, destructiveHint=true, and openWorldHint=true. The description adds non-contradictory context: it clarifies that the tool performs no external research or outbound actions (fleshing out openWorldHint) and discloses the paid nature and explicit wallet authorization requirement. It also notes the output is a draft for human review. It does not mention destructive side effects, but the annotation already signals that; the description adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, and every sentence adds information (output, constraints, payment). No filler or redundancy. It is appropriately concise for the complexity it conveys.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters, nested objects, no output schema, and 0% schema coverage. The description does not explain the purpose of result_expires, idempotency_key, result_signature, or payment_signature, nor does it describe the expected return format beyond 'draft for human review'. Given the complexity, the description leaves significant gaps that an agent would need to resolve before calling the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It mentions 'brand brief' and 'payment requires explicit wallet authorization', which partially maps to the 'brief' field and 'payment_signature' parameter, but it does not explain 'result_expires', 'idempotency_key', 'result_signature', or the nested 'input' object's fields beyond the brief. The description is insufficient to guide correct parameter usage for a 5-parameter schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb 'Create' and the resource: 'voice principles, vocabulary guidance, examples, and editing rules'. It also specifies the source ('supplied brand brief') and the output ('draft for human review'), making it distinct from sibling copy tools that target different deliverables like ad copy or blog drafts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use this tool: when a brand brief is supplied and the user wants voice principles. It also states constraints: 'Uses buyer-supplied information only; no external research or outbound actions.' However, it does not explicitly name alternatives or state when not to use it, so it stops short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

This is unusually transparent beyond the annotations: it states that the tool will avoid invented financial results, uses buyer-supplied information only, performs no external research or outbound actions, returns a draft for human review, costs 0.25 USD, and requires explicit wallet authorization. This complements the destructiveHint and readOnlyHint flags by explaining the real side effect (payment) and the human-review safeguard.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is tightly packed with no filler: purpose, constraints, output nature, price, and payment guardrail each earn their place in short, readable sentences. The core function is front-loaded, and the operational caveats are stated efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete enough for an agent to decide whether to call the tool and to understand the key constraints and cost. However, with no output schema and five parameters at 0% schema description coverage, the non-obvious expiration, idempotency, and signature fields remain unexplained, and the return structure is only described generically as 'a draft for human review'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description only loosely gestures at the input via 'buyer-supplied information' and at payment via 'wallet authorization'. It does not explain result_expires, idempotency_key, result_signature, payment_signature, or how audience maps to the input object, so an agent receives little parameter-level guidance beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Structure supplied business assumptions into a plan' and lists concrete deliverables (evidence gaps, experiments, milestones). It clearly identifies what the tool produces, though it does not explicitly contrast it with sibling planning tools such as launch_plan or project_plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: when a buyer has supplied business assumptions and source material for a business plan. It also states a meaningful when-not condition by saying there is no external research or outbound actions, so an agent should not reach for this tool when research is required. It does not name alternative sibling tools, which keeps it from a top score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the annotations: annotations declare openWorldHint=true (suggesting external interactions) and destructiveHint=true (implying possible destructive actions), while the description states 'no external research or outbound actions' and 'Returns a draft for human review' (implying no side effects). This is a clear contradiction, so the score is 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with purpose, and includes essential business details (price and payment authorization) without fluff. It could be more structured (e.g., explicit parameter list), but it is appropriately sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the nested object, 5 parameters, and no output schema, the description should clarify parameter semantics and side effects. It only states the output ('draft for human review') and pricing, but omits parameter usage and contradicts annotations, leaving critical gaps for an agent deciding to call it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the tool description must explain the parameters. It only mentions 'supplied evidence' generically and does not clarify what 'brief', 'source_text', 'audience', or the payment/expiry fields do. The description fails to compensate for the lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Build explicitly labeled persona hypotheses from supplied evidence'. It also clarifies a constraint ('avoiding sensitive personal profiling') that distinguishes it from generic content tools. Although it doesn't name sibling tools, the purpose is unambiguous and distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (when you have buyer-supplied evidence and want a persona draft) but provides no explicit guidance on when not to use it or which sibling tool to choose instead. It mentions constraints (no external research) but not alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the annotations. Annotations set openWorldHint=true, implying external access, but the description says 'no external research or outbound actions'. Similarly, destructiveHint=true conflicts with the non-destructive nature of building a model and returning a draft. Per the rule, any contradiction yields score 1. The description does add valuable behavioral context (price, payment authorization, draft for review) but the contradiction overrides that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loads the primary action. It includes necessary operational details (price, payment requirement, draft output) without verbosity. Each sentence adds relevant information. It could be marginally more structured, but it is efficient and appropriate in length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 5 parameters, a nested required object, and no output schema, the description is too thin. It fails to explain the meaning and format of the parameters, how payment authorization works, or what the returned draft looks like. The agent would lack essential details to use the tool correctly, especially given the contradiction with annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the meaning of the parameters. It does not. The description mentions 'supplied volumes and processing times' but does not map them to the actual parameters (brief, source_text, audience, result_expires, idempotency_key, etc.). The nested 'input' object with 'brief' and 'source_text' is not explained, leaving the agent to guess how to populate fields correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Build a capacity model from supplied volumes and processing times'. It clearly states the input and the expected deliverable, and the scope ('showing assumptions and missing inputs') distinguishes it from generic planning tools like account_plan or staffing_requirements. The title and name reinforce the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

While the description notes that only buyer-supplied information is used and no outbound actions are taken, it does not explicitly state when to choose this tool over siblings such as account_plan or staffing_requirements. There is no mention of alternative tools or conditions that would make another tool more appropriate, so the agent gets no routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description says 'no external research or outbound actions' while the annotations set openWorldHint=true, indicating the tool may interact with the open world. This is a direct contradiction. The description does add useful payment and no-invention context, but the contradiction forces a low score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well ordered: core action first, then constraints, return behavior, and pricing. Every sentence earns its place with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the task, constraints, return nature, and cost, which is good. But with an opaque 5-parameter schema, nested objects, no output schema, and a payment flow, it leaves critical invocation details unexplained, especially parameter mapping and wallet authorization mechanics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate by explaining parameters, but it never mentions brief, audience, source_text, payment_signature, or how they relate to 'customer evidence.' An agent cannot determine how to populate the nested input object from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Organize') and resource ('supplied customer evidence into challenge, approach, results, and missing proof'), making the tool's purpose clear. It does not explicitly name an alternative sibling, but the concrete output structure distinguishes it from generic outline tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for use: it should be fed buyer-supplied customer evidence and must not perform research or invent outcomes. However, it does not explicitly state when to prefer this tool over sibling tools or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the annotations by explicitly disclosing that the tool charges 0.25 USD and requires explicit wallet authorization, matching the destructiveHint. It also states that the output is only a draft for human review and that it makes no external research or outbound calls. This is valuable context for an agent deciding whether to invoke a paid, state-changing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the core purpose, followed by constraints, output nature, and payment details. Each sentence contributes information an agent needs, with no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the main operational aspects: what input to provide, what output to expect, and the payment requirement. However, it does not explain how the nested input fields map to the task (e.g., what 'brief' versus 'source_text' means), and it does not describe the mechanics of result signature or expiry fields. For a paid tool with no output schema, this is a noticeable gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate, but it mentions only that input comes from supplied products/services and buyer-supplied information. It does not clarify the roles of 'brief', 'source_text', 'audience', or the payment/result signature fields. This leaves the agent to guess parameter semantics from names alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Write category-page copy'), a clear resource ('category-page'), and the input source ('supplied products/services'). It also names two distinct deliverables (selection guidance, internal-link suggestions), which sets it apart from sibling copywriting tools like homepage_copy or service_page_copy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates when to use the tool: when category-page copy is needed from buyer-supplied product/service information. It also implies a limitation ('no external research or outbound actions'), which helps agents avoid using it for research-heavy tasks. However, it does not explicitly name alternative tools or exclusion criteria beyond that constraint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the annotation 'openWorldHint: true' by stating 'Uses buyer-supplied information only; no external research or outbound actions.' This is a serious inconsistency. While it does add pricing and payment context, the contradiction with structured data forces a low score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no filler. The core action is front-loaded, followed by input constraints and commercial terms. Each sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid tool with 5 parameters, a nested required object, and no output schema, the description is thin. It does not explain operational parameters or the return structure beyond 'draft for human review,' and the annotation contradiction introduces further uncertainty.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description must compensate for all parameter meanings. It only hints at source_text ('supplied company sources') and payment ('payment requires wallet authorization'), leaving brief, audience, result_expires, idempotency_key, and result_signature unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Summarize'), resource ('supplied company sources'), and output components ('business model, offerings, customers, and evidence gaps'). It also explicitly scopes out external research and outbound actions, which differentiates it from sibling tools that might perform broader research.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly indicates the tool is for summarizing buyer-supplied company sources only and not for external research, providing a usable when/when-not context. However, it stops short of naming sibling alternatives or giving explicit 'use this instead' guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the openWorldHint annotation: it claims 'no external research or outbound actions,' while openWorldHint=true indicates the tool may interact with the outside world. Payment requiring wallet authorization also suggests an outbound side effect, compounding the inconsistency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: what it does, how it scopes inputs, what it returns, and payment requirements are covered in three sentences. Every sentence adds necessary information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, non-idempotent tool with five parameters, no output schema, and zero parameter descriptions, critical operational details are missing: exact required inputs, how payment authorization is provided, what the draft output contains, and how the source citations appear. The description gives a high-level overview but is incomplete for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description must compensate but only loosely maps to parameters by referring to 'supplied competitor information' and 'provided source.' It does not explain brief, audience, source_text, idempotency_key, result_expires, or the payment/signature parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb and resource: compare supplied competitor information using an explicit matrix and cite supporting sources. It also differentiates itself from external-research tools by explicitly saying it uses buyer-supplied information only and performs no external research.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: use this when you have supplied competitor information, want a matrix-based comparison with source citations, and do not want external research. It does not explicitly name alternative tools or provide a when-not-to-use statement, so it stops short of full guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false, so the write nature is known. The description enriches this with specific behavioral details: it requires human review, charges 2.5 USD, demands explicit wallet authorization, and enforces content constraints (no invented promises/testimonials/imagery). This goes beyond the schema and annotations, though it does not detail the full workflow or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with zero wasted words. The first sentence leads with the core action and inputs, the second explains the mechanism (bounded planner, deterministic templates), and the third covers constraints and pricing. Every sentence adds distinct information, making it easy to scan and absorb.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers inputs, process, constraints, human review, and cost, but lacks any indication of output format or return value. Since there is no output schema, the agent cannot know what result to expect. It also leaves the payment/signature mechanisms under-specified, which is risky for a tool that explicitly requires wallet authorization.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain individual parameters beyond vaguely mentioning services and assets. The nested input object's fields like business_name, location, request_url, and the various signature parameters are undefined in both schema and description. For a paid, destructive tool, this is insufficient – the agent is left guessing which parameters are essential and how signatures relate to payment.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Create'), a concrete deliverable ('14-day campaign and newsletter'), and explicit input sources ('buyer-supplied services and authorized assets'). The phrase 'evidence-based' and 'bounded planner' differentiate it from generic content creation tools by emphasizing constraint and determinism, setting it apart from siblings like newsletter_draft or social_calendar.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied through phrases like 'explicit buyer-supplied services and authorized assets' and 'No invented promises', which suggests when this tool is appropriate (when evidence assets are available). However, it never explicitly names alternatives or states conditions for when not to use this tool, leaving the agent to infer from the many sibling content tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds useful context about payment, wallet authorization, and returning a draft. However, it directly contradicts the openWorldHint=true annotation by claiming 'no external research or outbound actions,' which is a serious inconsistency about whether the tool can access outside data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with no filler: it leads with the core action, then states constraints and payment requirements. Every sentence contributes a distinct fact an agent needs before calling the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a paid, destructive, non-idempotent tool with five parameters and no output schema, yet the description does not explain how to construct the nested input object or what result_signature/result_expires are for. The openWorldHint contradiction further reduces an agent's ability to predict the tool's behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain the nested input parameters such as brief, source_text, audience, or the optional result_expires/idempotency_key fields. It only hints at the overall input type by mentioning supplied content and payment authorization, which is insufficient for a five-parameter nested schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Compare'), names the resource ('supplied site/competitor content'), and names the deliverable ('evidence-backed coverage gaps and priorities'). This clearly distinguishes the tool from content-generation or comparison siblings, even without naming alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the intended use case: analyze supplied site/competitor content for coverage gaps. It adds constraints such as 'buyer-supplied information only' and 'returns a draft for human review,' but it does not explicitly state when to choose this tool over siblings or list when-not-to-use conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructiveHint=true and openWorldHint=true, but the description clarifies that despite these, the tool performs no external actions and returns a draft for review, which mitigates the destructive connotation. It also discloses pricing and payment authorization requirements, which is valuable beyond annotations. The description adds context that helps the agent understand the tool's safety and scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, three sentences, with the core purpose and scope front-loaded. It covers key behavioral constraints, return expectation, and pricing/payment in a compact form. Each sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, constraints, and payment, but given the nested input schema with multiple parameters and 0% schema coverage, it lacks critical details on how to structure the input fields. No output schema exists, so the description should hint at what the returned draft looks like, but it only says 'Returns a draft for human review.' This is insufficient for a tool with such a complex schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain any parameters. The 'input' object is nested with properties like 'brief', 'audience', and 'source_text', but the description gives no hint about their roles or required format. The payment_signature and other technical parameters are also unexplained. The description fails to compensate for the lack of schema documentation, making it hard for an agent to construct valid calls.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Adapt'), resource ('supplied copy'), and target ('requested language and region'), and mentions marking cultural/terminology uncertainties. It distinguishes itself from generic copywriting siblings by emphasizing localization and no external research. However, it does not explicitly name a sibling alternative, so it doesn't fully leverage differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states the tool uses buyer-supplied information only, performs no external research or outbound actions, and returns a draft for human review. This implies when to use it (when you have source text and a brief) and excludes scenarios requiring external research. However, it doesn't explicitly name alternative sibling tools for similar functions, so the guidance is clear but not comparative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds useful information about payment, human review, and input-source constraints, but it directly contradicts the openWorldHint=true annotation by claiming 'no external research or outbound actions.' This is a major conflict between declared behavior and the tool's annotation, and per the rules any such contradiction caps this dimension at 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four short sentences with no filler or redundancy. The primary function is front-loaded first, followed by constraints, output status, and cost/payment. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core transformation, buyer-supplied-only constraint, draft output, and price, but it lacks parameter-level guidance, return-format details, and explicit reconciliation with the contradictory annotations. Without an output schema, more behavioral and invocation detail is needed for an agent to call this tool reliably.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden of explaining parameters. It vaguely maps to source_text via 'supplied long-form content' and mentions wallet authorization for payment, but it does not explain the required 'brief', the optional 'audience', or the cryptic top-level fields like idempotency_key, result_expires, result_signature, and payment_signature. This is insufficient for a 5-parameter schema with nested objects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Transform'), a precise resource ('supplied long-form content'), and the expected output ('a set of shorter assets with source references and distribution guidance'). This makes it distinguishable from sibling content tools like document_summary or content_localization without needing to open schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: when the user supplies long-form content and wants repurposed assets with distribution guidance. The constraint 'Uses buyer-supplied information only; no external research or outbound actions' functions as an implicit exclusion for use cases requiring market research or external sources, though it does not explicitly name an alternative sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Even though annotations already mark readOnlyHint false and destructiveHint true, the description adds valuable behavioral detail: preservation of string values/duplicate headers/ragged rows, no type inference, default spreadsheet-formula escaping with alteration reports, maximum rows/columns, and explicit payment authorization requirement. These go beyond the annotations and help anticipate side effects and prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: four sentences, each adding distinct value (conversion purpose, data-handling behavior, limits, and commercial terms). The core function is front-loaded, and there is no redundant or filler text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a paid, state-changing tool with a nested input object and five parameters, yet the description omits how payment authorization works, the role of result_expires/idempotency_key/result_signature, and the exact output structure. The limits and payment requirement are useful, but the definition is not complete enough for an agent to call the tool correctly without further investigation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description must compensate, but it only implicitly references delimiter and spreadsheet_safe. It does not explain the purpose or format of payment_signature, idempotency_key, result_expires, or result_signature, which are non-obvious for a conversion tool and critical for correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('convert') with a clear resource (CSV/JSON string rows) and both directions (csv_to_json and json_to_csv). It further distinguishes itself by detailing behavior such as preserving duplicate headers, ragged rows, and no type inference, which separates it from extraction or validation siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives, and no sibling tool is named as a substitute. The description provides capabilities and constraints (row/column limits, payment) but leaves the agent to infer use cases from the purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds meaningful behavioral context beyond annotations: it returns a draft for human review (not a final deliverable), uses only buyer-supplied information, performs no outbound actions, and has a price of 0.25 USD requiring explicit wallet authorization. This is valuable for an agent deciding whether to invoke the tool. The annotations (destructiveHint=true) are not contradicted; the description's 'draft for human review' implies non-destructive output, but the annotation may refer to payment side effects, which the description discloses.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each carrying distinct information: what it produces, input constraints, output nature, and cost/payment requirement. No filler or repetition. The most important information (what it does) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core behavior, constraints, and payment, but with no output schema and 5 parameters (including payment_signature and result_signature), an agent might need more detail on how to provide the payment signature or what the result signature means. The nested 'input' object is partially explained, but the auxiliary parameters are not. For a paid tool with destructiveHint=true, this is a moderate gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions 'supplied goals' which maps to the 'brief' parameter, and 'buyer-supplied information' maps to 'source_text', but it doesn't explain 'audience', 'result_expires', 'idempotency_key', 'result_signature', or 'payment_signature'. The description adds some context for the main inputs but leaves the payment/result parameters unexplained, which is a gap given zero schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Turn supplied goals into...') and resource (customer success plan), listing concrete outputs: onboarding milestones, adoption actions, ownership, measurable outcomes. It distinguishes itself from siblings like account_plan by focusing on customer success/onboarding, though it doesn't explicitly name a sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states the input source ('buyer-supplied information only') and constraints ('no external research or outbound actions'), which tells the agent when this tool is appropriate. It doesn't explicitly name alternatives or exclusions, but the constraints imply when not to use it (e.g., when external research is needed).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotations. Annotations mark openWorldHint=true (external access) but description says 'no external research or outbound actions'. Also destructiveHint=true conflicts with the description's non-destructive 'returns a draft' behavior. While it transparently states price and payment authorization, these contradictions seriously undermine behavioral clarity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief and front-loaded with the core purpose. It includes necessary operational details (price, payment authorization) without excessive fluff. The structure is efficient, though the pricing/payment info could be more integrated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a nested input object and several signature/idempotency parameters, but the description explains none of them. It lacks any mention of required vs optional fields, how to construct the input, or what the output draft looks like. Given the complexity, this is insufficient for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description provides no explanation of any parameters (input object, result_expires, idempotency_key, result_signature, payment_signature). The description does not add meaning beyond the schema fields, leaving agents to guess how to populate them correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Review') and resource ('supplied schema/sample rows'), and specifies the outcome ('propose specific validation rules and correction actions'). This distinguishes it from sibling tools like tradepilot_service_schema_suggestions, which focuses on schema changes rather than quality review.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides some context: it uses only buyer-supplied information, no external research, and returns a draft for human review. However, it does not explicitly mention alternatives or conditions for when to use this tool over others. The absence of explicit comparisons leaves usage guidance implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotations: it claims 'no external research or outbound actions' and 'Uses buyer-supplied information only,' while openWorldHint=true signals that the tool may access open-world/external resources. It does usefully add cost and wallet-authorization details, but per the contradiction rule this dimension must score 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: core purpose first, then constraints, then commercial terms. The payment and no-outbound clauses could be grouped more tightly, but every sentence carries necessary information and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid tool with 5 parameters, a nested required object, no output schema, and no parameter explanations, the description leaves too much unstated. It explains the high-level workflow and cost, but the agent still lacks the information needed to construct a valid request or understand the response beyond 'a draft.'

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description carries the full burden of explaining parameters, but it never mentions `input`, `brief`, `source_text`, `audience`, or any technical fields like `result_signature` or `payment_signature`. An agent cannot reliably map the high-level intent to the required nested `input` object.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('Compare supplied options'), a method ('using stated criteria, tradeoffs, unknowns'), and a deliverable ('a reasoned recommendation ... draft for human review'). This clearly establishes what the tool does and separates it from generic comparison or summary tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for use: analyze buyer-supplied information and produce a decision memo, while explicitly ruling out external research and outbound actions. It does not list sibling alternatives or explicit when-not-to-use cases, but the boundary is strong enough for an agent to route to this tool in closed-world decision analysis.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare openWorldHint=true, implying the tool may access external resources, but the description explicitly states 'no external research or outbound actions,' which directly contradicts the annotation. This is a serious inconsistency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences and front-loads the core purpose, followed by constraints and payment info. It is efficient and avoids fluff, though it could be slightly more structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and unclear parameter semantics, the description leaves major gaps: it does not specify what the draft format is, what the input should contain beyond 'product and buyer situation,' or how the payment flow works beyond a vague 'explicit wallet authorization.' It is incomplete for a paid tool with complex parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description mentions none of the five parameters (input, result_expires, idempotency_key, result_signature, payment_signature). It does not compensate for the missing schema documentation at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool develops a 'sequenced discovery-question guide' tied to the supplied product and buyer situation, which is specific and distinguishes it from sibling tools like sales_call_script or testimonial_questions. The verb and resource are precise.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies constraints: 'Uses buyer-supplied information only; no external research or outbound actions,' which clarifies when it should be used. However, it does not explicitly name alternative tools or provide exclusion criteria, so it stops short of full guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare openWorldHint=true, but the description says 'Uses buyer-supplied information only; no external research or outbound actions,' which directly contradicts that annotation. The description also fails to explain the destructiveHint=true trait, leaving the behavioral profile inconsistent and unclear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the main purpose, and each sentence adds practical context: scope of comparison, no-legal-advice boundary, no-outbound-behavior, output format, and payment requirement. It is compact with no meaningful filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and zero parameter documentation, the tool needs a stronger description to be safely invocable. The description mentions that it returns a draft and requires payment authorization, but it doesn't specify required input structure, signature/expiration semantics, or how the draft is delivered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden of explaining parameters, but it only alludes to 'supplied documents' and 'explicit wallet authorization.' It does not clarify the roles of brief, source_text, audience, result_expires, idempotency_key, result_signature, or payment_signature.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('Compare the supplied documents') and the target output types ('substantive changes, omissions, conflicts, and questions'), so an agent can tell this is a semantic document comparison tool. It doesn't explicitly differentiate from sibling tools like text_line_compare, but the word 'document' and 'substantive' convey the intended scope reasonably well.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives useful constraints such as 'do not give legal advice' and 'no external research or outbound actions', and it notes the result is a draft for human review. However, it gives no guidance on when to choose this tool over alternatives like text_line_compare or document_summary, nor any exclusion criteria for when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotation openWorldHint: true by explicitly stating 'no external research or outbound actions.' This is a direct contradiction. While it discloses payment and wallet authorization, the contradiction lowers the score to 1 per the rubric.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with no fluff. It front-loads the purpose, includes key constraints (no external research), output (draft for human review), and pricing/payment details. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool's complexity (5 params, nested object, no output schema), the description omits parameter meanings, idempotency, signature requirements, and output format details. It covers high-level constraints but leaves critical invocation details undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain any of the 5 parameters (input, result_expires, idempotency_key, result_signature, payment_signature). It only mentions 'supplied document text' without mapping to the actual schema fields, failing to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool summarizes supplied document text, listing main points, evidence, caveats, and source section references. This distinguishes it from sibling tools that target specific content types like ad copy or blog drafts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context by stating it uses buyer-supplied information only and no external research, indicating when it's appropriate. However, it does not explicitly mention alternatives or when not to use it, so it lacks exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructive and non-idempotent behavior, and the description adds that payment requires explicit wallet authorization and human review is needed. However, it doesn't detail what side effects or destructive actions occur beyond payment, leaving some ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with the primary purpose front-loaded, followed by essential caveats about cost and review. Every sentence adds value with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and many undocumented parameters, the description lacks essential details such as return format, meaning of payment fields, and side effects. It provides a high-level summary but is insufficient for an agent to fully understand invocation expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions 'dimensions' and 'product details' which hint at parameters like door_width_in, but it fails to explain payment_signature, result_expires, idempotency_key, or other fields. This leaves many parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a door/swing/SlideDrive configuration and price range from dimensions and product details. This distinguishes it from the many content-generation siblings, though it could be more explicit about what 'product details' entails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It mentions the tool is a free preliminary estimate requiring human review, which gives context on when to use it, but it doesn't explicitly compare against alternatives or state when not to use it. The guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explicitly states 'no external research or outbound actions', but the annotation openWorldHint is true, which typically indicates the tool may access external data. This is a direct contradiction. Additionally, the description mentions payment authorization and returns a draft, but the contradiction with the annotation undermines transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with three sentences covering purpose, constraints, and payment. However, it front-loads the purpose but then mixes constraints and payment details without a logical structure. It is not verbose, but the information is not optimally organized for quick scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 parameters including a nested input object, no output schema, and contradictory annotations, the description is inadequate. It omits parameter explanations, result format details, and clear payment mechanics beyond a mention. The tool is complex enough that a more thorough description is required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides no information about any of the parameters (e.g., 'brief', 'source_text', 'audience', or the signature fields). The description only references 'the supplied offer' without mapping to the schema, leaving agents with no guidance on what to fill in.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates email subject lines and preview text, grounded in the supplied offer. It specifies the resource ('email subject lines') and the action ('generate'). However, it does not explicitly differentiate from sibling tools like 'headline_variants' or 'ad_copy', though the email-specific focus helps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: 'grounded in the supplied offer' and 'Uses buyer-supplied information only' suggest it is for creating subject lines from provided materials. It does not state when to avoid this tool or mention alternative tools, leaving the agent to infer from the name and siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explicitly states 'no external research or outbound actions,' which directly contradicts the annotation openWorldHint=true. Although it does disclose the price and wallet authorization requirement, the contradiction makes the safety model unreliable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four short sentences with the core action front-loaded. The human-review, price, and payment authorization details are all relevant, and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a paid, five-parameter tool with no output schema and no parameter semantics. Critical invocation details around signatures, expiry, and nested input fields are unexplained, and the open-world contradiction further undermines completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description maps no parameters: it never explains input.brief, input.audience, result_expires, idempotency_key, result_signature, or payment_signature, nor the required nested input object. 'Supplied text' is the only clue and does not compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb ('Extract'), a precise scope ('explicitly stated organizations, products, places, dates, and business terms'), and an output feature ('evidence snippets'), which distinguishes it from general siblings like structured_extraction and requirements_extraction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context: use this only on buyer-supplied text, with no external research or outbound actions. It does not name sibling alternatives or exclusion conditions, so it stops short of a full when-to-use guide.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the openWorldHint annotation: it states 'no external research or outbound actions' while openWorldHint=true implies potential external world access. This is a clear annotation contradiction. Additionally, it doesn't clarify the destructiveHint=true annotation or the payment authorization details beyond a mention, so the description misleads rather than adds value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no fluff. It front-loads the core action (condense), then scope, then return type, then cost/payment. Every sentence adds useful information, and the structure is logical and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid tool with nested required parameters and no output schema, the description omits critical details: what constitutes a valid 'brief', how to provide 'source_text', how payment_signature works, and what the draft output format looks like. The contradiction with openWorldHint further reduces reliability, leaving an agent under-equipped to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate by explaining what parameters like 'brief', 'source_text', and 'audience' mean. However, the description provides no parameter-specific semantics at all. An agent cannot determine how to fill the required 'input' object or what 'brief' vs 'source_text' should contain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool condenses supplied material into decision-relevant findings, evidence, risks, and actions, and returns a draft for human review. This specific verb+resource+output distinguishes it from sibling tools like decision_memo or meeting_brief.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clarifies that the tool uses only buyer-supplied information and performs no external research or outbound actions, which helps an agent avoid misusing it for tasks requiring external data. However, it doesn't explicitly name alternative tools or conditions for choosing this one over others, leaving some inference needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the annotations: it states 'Uses buyer-supplied information only; no external research or outbound actions,' while annotations set openWorldHint to true, implying the tool may interact with the external world. This is a clear contradiction. Additionally, the destructiveHint true is not explained, but the openWorld contradiction is sufficient to score 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with three sentences that front-load the core purpose, then add behavioral constraints and payment terms. It avoids fluff and is easy to parse. The payment and price details are relevant but could be considered secondary; still, the structure is efficient and well-ordered.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, 0% schema coverage, nested objects, and no output schema, the description is not complete. It does not clarify what should go inside 'input.brief' versus 'input.source_text', nor what the signatures and expiration fields are for. It mentions returning a draft for human review but omits important parameter context, leaving an agent under-informed for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not elaborate on the parameters. It only says 'supplied business information' and mentions payment authorization, but it does not explain the required 'brief' or 'source_text' fields, the optional 'audience', or the purpose of result_expires, idempotency_key, result_signature, and payment_signature. This leaves agents without essential parameter guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb-resource pair: 'Draft useful questions and answers from supplied business information.' It also adds the distinguishing behavior of 'marking answers that require confirmation.' This makes the tool's purpose unambiguous and distinct from siblings like objection_responses or discovery_questions, even without naming them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: it is for drafting an FAQ from buyer-supplied information, explicitly notes that no external research or outbound actions are performed, and indicates the output is a draft for human review. It does not name specific alternative tools or exclusion conditions, but the context is enough for an agent to select it over research-based siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=false, destructiveHint=true, and openWorldHint=true, but the description adds valuable context: it uses only buyer-supplied information, performs no external research or outbound actions, returns a draft for human review, and requires explicit wallet authorization for payment. This goes beyond the annotations and clarifies the tool's safety and workflow profile. It does not contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, each adding distinct information: core function, data scope, output nature, and pricing/payment requirement. It is front-loaded with the primary purpose and wastes no words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, data scope, output, and payment flow, which is substantial for a tool with no output schema. However, it does not explain the meaning of several input parameters (e.g., idempotency_key, result_signature, payment_signature) or the expected format of the returned draft. Given the tool's complexity and the absence of an output schema, the description is adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden of explaining parameters. It mentions 'supplied source fields' and 'target schema', which loosely maps to the 'input' object's 'source_text' and 'brief' fields, but it does not explain the purpose of 'audience', 'result_expires', 'idempotency_key', 'result_signature', or 'payment_signature'. The description adds some semantic context but leaves significant gaps for a 5-parameter tool with nested objects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Map'), a clear resource ('supplied source fields to a target schema'), and enumerates the core deliverables: transformations, required validation, and unmapped fields. This distinguishes it from the many sibling content-generation tools, which focus on copywriting or research rather than structured field mapping.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states the tool's scope: it uses buyer-supplied information only and performs no external research or outbound actions. This helps an agent know when to choose it over research-capable siblings. However, it does not explicitly name alternative tools or state when not to use it, leaving some inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations mark the tool as openWorldHint=true and destructiveHint=true, while the description claims it 'uses buyer-supplied information only,' performs 'no external research or outbound actions,' and returns a draft for human review. This is a direct conflict in safety signals: either the annotations overstate side effects or the description understates them. The agent cannot trust the behavioral model.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three compact sentences with no filler. Purpose, input constraints, output behavior, and pricing/payment are each addressed in a front-loaded, scannable way.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, zero parameter descriptions, and a contradiction with the annotations, so the definition does not give an agent enough to confidently construct a correct call. The high-level purpose is clear, but payment mechanics, parameter semantics, and side-effect behavior remain ambiguous.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate by explaining the parameters. It only gestures at 'meeting or conversation notes' and 'buyer-supplied information,' leaving brief, source_text, audience, result_expires, idempotency_key, result_signature, and payment_signature semantically unexplained. It also does not map 'explicit wallet authorization' to the payment_signature field.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific action ('Draft a follow-up') and specifies the source ('supplied meeting or conversation notes') and content scope ('confirmed actions and dates only'). This clearly distinguishes it from sibling drafting tools such as outreach_email_draft or newsletter_draft.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: use it for follow-up drafts from buyer-supplied notes, and it explicitly states that no external research or outbound actions are performed. It does not name alternatives or state explicit when-not-to-use conditions, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the openWorldHint annotation: openWorldHint=true suggests access to external world information, while the description explicitly says 'no external research or outbound actions.' The description does provide useful context about payment and human review, but the direct contradiction with an annotation forces a score of 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact three-sentence definition with no wasted words. It front-loads the core function, then gives scope constraints, output expectations, and pricing/authorization requirements, all of which are decision-relevant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no parameter descriptions, the agent is left without enough detail to construct a valid request, especially the meaning of brief versus source_text versus audience. The payment and no-external-research constraints are helpful, but the openWorld contradiction and parameter gaps make the definition incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the five parameters, but it does not explain what belongs in input.brief, source_text, audience, or the various signature/expiry fields. The only implicit mapping is 'buyer-supplied information' roughly pointing to input, which is insufficient for a nested-object request.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb-resource pair: edit supplied text for grammar and clarity while preserving facts and intent, and mentions that meaningful changes are summarized. It does not explicitly distinguish itself from sibling rewrite tools like tone_rewrite or plain_language_rewrite, but the focus on grammar/clarity plus the change summary is reasonably specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is appropriate when a buyer-supplied text needs grammar and clarity editing without external research, and it warns that payment requires explicit wallet authorization. It does not state when to prefer an alternative tool or when not to use this tool, leaving some routing decisions to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states 'no external research or outbound actions', which directly contradicts the annotation openWorldHint=true, which typically indicates the tool may access external data. This is a clear contradiction. While the description does disclose payment requirements (destructiveHint), the contradiction forces a score of 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, and includes essential constraints (no external research, draft output, price, payment). Every sentence adds value with no redundancy or fluff. It is well-structured and easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has five parameters, a nested object, no output schema, and annotations that partially conflict. The description covers the purpose, constraints, and payment, but omits any explanation of the input parameters or the output format beyond 'a draft for human review'. Given the complexity, this is incomplete. The contradiction with openWorldHint also reduces completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate by explaining parameters. It does not mention any of the five parameters, including the required 'brief' or optional ones like 'idempotency_key' or 'payment_signature'. The only hint is 'Uses buyer-supplied information only', but that is insufficient to guide an agent on how to populate the schema. The description fails to provide any parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Produce') and resource ('headlines'), and details the output format ('grouped by angle, with rationale and unsupported-claim checks'). It clearly distinguishes this tool from siblings like email_subject_lines by focusing on headline generation for a workshop. The scope is explicit and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool: it uses buyer-supplied information only and performs no external research or outbound actions, implying it is appropriate when the buyer's input is sufficient. It also notes the result is a draft for human review, signaling it's not a final output. However, it does not explicitly name alternative tools or state when not to use it, leaving some room for inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states 'no external research or outbound actions,' but the annotations declare openWorldHint=true, meaning the tool may interact with the outside world. This is a direct contradiction. The payment and human-review details add useful context, but the contradiction requires a score of 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded. Each sentence earns its place: scope, input constraint, output expectation, price, and payment requirement. There is no filler or redundant restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid tool with five parameters, no output schema, and zero parameter documentation, this description is under-specified. It states that a draft is returned but not its structure, when to choose this over sibling copy tools, or how the signature and idempotency parameters behave. The openWorld contradiction further undermines reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the five parameters, but it only gestures at buyer-supplied content and payment authorization. It does not explain result_expires, idempotency_key, result_signature, or payment_signature, leaving an agent unable to populate them correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Draft homepage sections' and enumerates the content areas (business, audiences, products, proof, navigation priorities). It is clearly a homepage copywriting tool, though it does not explicitly distinguish itself from closely related siblings like landing_page_copy or about_page_copy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance or alternative routing. It does not say to prefer this over related copy tools, nor does it mention prerequisites beyond 'buyer-supplied information.' The buyer-supplied constraint implies a condition, but no explicit usage direction is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds meaningful behavioral context beyond the annotations: it states the tool uses only buyer-supplied information, performs no external actions, returns a draft for review, costs 0.25 USD, and requires explicit wallet authorization. While destructiveHint is true, the payment warning is consistent with that annotation, and the 'no outbound actions' line prevents misreading the tool as modifying external systems.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four short sentences with no filler. It front-loads the core function, then adds scope constraints, output format, price, and authorization requirement. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 0% schema coverage, no output schema, and a nested required input object, the description is too high-level for a correct invocation. It does not explain how to supply URLs or authorization details, nor does it clarify the payment-signature mechanism. The agent knows what the tool produces but not enough about how to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides almost no parameter-level guidance. It does not explain the relationship between 'brief,' 'source_text,' and 'audience,' nor how the payment and signature fields (payment_signature, result_signature, result_expires, idempotency_key) should be populated. An agent is left to infer field semantics from names alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Recommend links among supplied URLs with anchor text, relevance rationale, and implementation priority.' This clearly identifies the deliverable and distinguishes it from sibling content-generation and SEO tools by emphasizing buyer-supplied URLs and no external research.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when the tool is appropriate: when a buyer has supplied URLs and wants an internal-link draft, with no external research or outbound actions. It stops short of explicitly naming alternatives or exclusion criteria, but the context is strong enough for an agent to route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description directly contradicts the openWorldHint annotation: it says 'no external research or outbound actions' while the annotation indicates the tool may access the open world. It also does not explain the destructiveHint=true annotation beyond mentioning payment authorization, and the 'Returns a draft' phrase does not address potential destructive side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the core purpose, followed by boundary conditions, output type, and pricing/authorization. There is minor redundancy between 'buyer-supplied information only' and 'no external research', but overall each clause contributes useful information without padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid tool with five parameters, nested input, no output schema, and non-trivial annotations, the description is incomplete. It does not explain parameter semantics, the exact structure of the returned draft, or how the payment_signature and result_signature work. The contradiction with openWorldHint also undermines an agent's ability to reason about side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no meaningful explanation for the five parameters. It only hints that the input is 'supplied text', which loosely maps to source_text, but it does not explain the required brief, audience, result_expires, idempotency_key, result_signature, or payment_signature.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Extract invoice fields from supplied text', and adds detail on preserving currency and identifiers and marking missing values. It explicitly excludes OCR and accounting posting, which differentiates it from related extraction tools like receipt_text_extraction and entity_extraction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives useful boundary conditions: it operates only on supplied text, not OCR, and does not post to accounting. It also clarifies that it uses only buyer-supplied information and returns a draft for human review. However, it does not explicitly name sibling alternatives or state when to prefer this over receipt_text_extraction, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark destructiveHint=true and readOnlyHint=false, but the description adds valuable behavioral details: handling escaped slashes/tilde, reporting missing paths, rejecting duplicate keys or lossy numbers, and the payment requirement with explicit wallet authorization. These go beyond the structured annotations and clarify the tool's operational behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, with the primary action front-loaded. Every sentence adds value: core operation, edge-case handling, and payment authorization. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 parameters, zero schema descriptions, and no output schema, the description is incomplete. It explains the core redaction behavior but omits parameter semantics, output format, error reporting details (what 'reports missing paths' looks like), and how to provide wallet authorization. An agent would struggle to correctly supply all parameters without additional info.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It only indirectly references the 'pointers' concept via 'RFC 6901-style JSON object paths' but does not describe the 'json' input, 'result_expires', 'idempotency_key', 'result_signature', or 'payment_signature' parameters. The payment mention hints at 'payment_signature' but lacks detail. This is insufficient for a 5-parameter tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'remove' with the resource 'explicitly named RFC 6901-style JSON object paths' and specifies the exact behavior for array elements (replace with null to preserve indices). It also distinguishes itself from automatic detection, which helps differentiate from potential sibling tools like a generic redaction tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Does not automatically detect sensitive information,' which tells the agent when to use this tool (when paths are known) and when not (when automatic detection is needed). However, it does not name a specific alternative tool or provide explicit when/not conditions beyond that, but the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds significant context beyond annotations: strict validation rules, the two-space formatting output, and the paid nature with wallet authorization. The annotations indicate readOnlyHint=false and destructiveHint=true, and the description's mention of payment and strict validation aligns with non-trivial side effects. No contradiction found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences deliver purpose, constraints, exclusions, price, and authorization requirement without fluff. The critical information is front-loaded, and every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid tool with no output schemaable and multiple undocumented parameters, the description lacks enough context. It explains the core functionality and output (formatted JSON) but omits parameter semantics, error behavior, and how the payment/authorization flow affects results. Some gaps are acceptable given the schema but the overall picture is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain any of the five parameters. The required 'input' is only implicitly hinted by 'Validate JSON', while parameters like result_expires, idempotency_key, result_signature, and payment_signature are completely opaque. The description fails to compensate for the schema's lack of semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Validate JSON and return two-space formatting.' It further distinguishes itself by listing what it rejects (duplicate keys, excessive nesting, non-representable numbers) and what it does not do (JSON Schema evaluation, remote reference fetching). This clearly separates it from the many content-generation sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-not-to-use guidance by excluding JSON Schema evaluation and remote reference fetching, which helps an agent avoid this tool for those needs. It also mentions the payment prerequisite ('requires explicit wallet authorization'). However, it does not name any alternative tool for schema validation or other use cases, so the guidance is not fully complete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states 'no external research or outbound actions', which directly contradicts the openWorldHint=true annotation (which indicates the tool may return information beyond inputs). Additionally, destructiveHint=true is not explained by the description, but it does mention payment requires explicit wallet authorization. The contradiction with openWorldHint is a serious inconsistency, so a score of 1 is warranted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, two sentences, and front-loads the core purpose. It includes necessary caveats about pricing and payment. However, it omits parameter details, which might be considered a completeness issue but not a conciseness issue. The structure is efficient with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the nested object schema, five parameters, and no output schema, the description is incomplete. It does not explain the purpose of idempotency_key, result_signature, payment_signature, or result_expires. It only vaguely mentions a draft for review. The contradiction with openWorldHint further undermines completeness. More detail on parameters and expected output is needed for an agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does not explain any of the parameters such as 'brief', 'source_text', 'audience', or the various signatures. The description mentions 'supplied keywords' but does not map them to any specific field. With three nested parameters and no description, the agent cannot infer parameter meanings from the description or schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Group supplied keywords by intent and topic'. It also adds a distinguishing detail: 'explain ambiguous groupings' and 'do not invent search volume', which differentiates it from siblings like search_intent or keyword_page_map. The mention of returning a draft for human review further clarifies its role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use: 'Uses buyer-supplied information only; no external research or outbound actions' and notes payment authorization. However, it does not explicitly mention alternatives or when not to use this tool versus siblings such as search_intent or keyword_page_map. It gives a clear context but lacks exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds valuable behavioral context beyond the annotations: it notes the tool 'Returns a draft for human review', mentions 'Price: 0.25 USD', and 'Payment requires explicit wallet authorization'. It also discloses the constraint of no outbound actions. These are not covered by the annotations (readOnlyHint=false, destructiveHint=true), so the description fills gaps without contradicting the schema. The destructiveHint is not explained, but the description implies a non-destructive analysis output, so no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loading the core purpose in the first sentence. It includes essential cost and authorization details without redundancy. Every sentence adds value—purpose, scope, and payment—so it is appropriately concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters, a nested object, and no output schema. The description is too brief to cover the complexity. It does not explain the input structure (e.g., what goes in 'brief' vs 'source_text') or the meaning of optional fields like idempotency_key or result_signature. While the schema defines the structure, the description should provide semantic context for how to populate these fields to achieve the mapping goal. The mention of 'draft for human review' hints at the output but does not describe the result format. This is insufficient for a tool with such an elaborate schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter meaning. However, the description does not map its actions to the actual schema fields. It mentions 'supplied keywords' and 'pages' but the schema has 'brief', 'audience', and 'source_text' within the 'input' object, plus several optional parameters like result_expires and payment_signature. The description does not clarify what these fields represent or how they relate to the mapping task. The agent would have to infer the mapping from names alone, which is insufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action: 'Map supplied keywords to supplied or proposed pages', and includes distinct behaviors like 'flag cannibalization' and 'separate existing from proposed URLs'. This clearly differentiates it from siblings like keyword_cluster (grouping) or internal_link_plan (link placement). The purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: 'Uses buyer-supplied information only; no external research or outbound actions.' This tells the agent when to use the tool (when working with buyer-provided data). However, it does not explicitly name alternatives or state when NOT to use it, so it lacks exclusions. This earns a 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which flag it as a non-read-only, potentially destructive operation), the description discloses that it returns a draft for human review, that it never performs external research or outbound actions, and that a 0.25 USD payment requires explicit wallet authorization. These are significant behavioral details not present in the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it opens with the core purpose, then states constraintsstal and pricing. No filler, redundancy, or unnecessary details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with five parameters, a nested input object, and no output schema, the description provides important operational context (draft result, cost, payment, no external actions) but leaves out details on the expected shape of the return value and does not compensate for the undocumented schema. Its ambiguity about the deliverable format prevents a higher score.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, and the description does not map its terms (brief, source_text, audience, payment_signature, etc.) to input semantics. The only parameter-related hint is that the tool uses buyer-supplied information and mentions the payment requirement, but it doesn't explain the content expected for the required object fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Define metrics with purpose, formula, source requirements, cadence, ownership, and interpretation limits,' naming a concrete verb and a well-specified deliverable. It aligns with the title 'KPI specification' and is clearly distinct from sibling content-generation tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the tool uses only buyer-supplied information and performs no external research or outbound actions, which sets clear constraints for invocation. However, it does not explicitly list when to prefer this tool over an alternative or provide when-not-to-use guidance, leaving usage to be inferred from the purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important behavioral constraints beyond the annotations: it uses only buyer-supplied information, performs no external research or outbound actions, returns a draft for human review, and requires explicit wallet authorization for the 0.25 USD fee. This provides strong context around the readOnlyHint, destructiveHint, and payment implications without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four concise sentences, front-loaded with the primary purpose and followed by short, relevant constraints, output format, and pricing. Every sentence adds necessary information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is strong at the selection level—purpose, constraints, output, and price are clear—but incomplete at the invocation level because there is no output schema and no parameter-level documentation. The agent still lacks guidance on how to structure the input object and what result-related fields mean.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden of explaining parameters, but it does not map behaviors to individual fields such as input.brief, source_text, audience, result_expires, idempotency_key, result_signature, or payment_signature. It gestures at 'supplied business examples' and 'wallet authorization,' but an agent would still need to infer how to populate several required or meaningful fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific deliverable: a non-overlapping label taxonomy built from supplied business examples, including definitions and ambiguous-case rules. This clearly differentiates the tool from siblings like text_classification or entity_extraction, which perform classification or extraction rather than taxonomy design.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool through phrases like 'from supplied business examples' and 'no external research,' but it never explicitly names alternatives or states when to prefer this over related tools such as schema_suggestions or field_mapping. Usage context is clear, but exclusion guidance is absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description claims 'no external research or outbound actions' while the annotations set openWorldHint=true and destructiveHint=true, which implies external side effects. The description also mentions payment requiring wallet authorization, which is an outbound action. This directly contradicts the annotation and the description's own later statement, making the behavioral model inconsistent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact: three sentences, with the primary action and deliverable front-loaded. The second and third sentences add important constraints and cost/authorization details without excessive padding. However, the misleading 'no outbound actions' claim introduces a structural inconsistency that costs it a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has nested objects, no output schema, and 0% parameter coverage. The description gives only a minimal view of output ('draft for human review') and omits how to construct the required 'input' object or what the expected return structure looks like. It does disclose price and authorization, which is useful, but an agent would still lack enough information to populate the parameters correctly or anticipate the full response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no parameter-level detail. It does not explain 'input', 'brief', 'audience', 'source_text', or the signature/expiry fields. The phrase 'buyer-supplied information' vaguely maps to the brief/audience/source_text, but no actual parameter names or requirements are mentioned, so the description fails to compensate for the absent schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete action: 'Draft a focused landing page' and lists the key sections (hero, benefits, evidence placeholders, objections, CTA). This clearly distinguishes it from siblings like homepage_copy, ad_copy, or value_proposition by naming the specific deliverable and its components.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives context: uses buyer-supplied information only, no external research, returns a draft for human review. It implies the tool is appropriate when the buyer has provided sufficient information and wants a draft, but it does not explicitly name alternatives or state when not to use this tool versus, say, homepage_copy or service_page_copy.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotations: it states 'no outbound actions' and 'no external research' while openWorldHint is true, which signals possible outside-world interaction. It also discloses payment and wallet authorization, but because of the direct contradiction, per rubric this dimension must score 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four compact sentences, each adding unique information: scope/deliverables, input limits, output nature, price/payment requirement. No filler and the core action is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The plan output, price, and human-review workflow are covered, but the description doesn't explain how to supply the required brief/source_text precisely, nor the expiry/idempotency/result-signature fields. Given no output schema and contradictory open-world behavior, the description is not complete enough for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must explain the parameters, but it only hints at buyer-supplied source input, audience, and wallet authorization. result_expires, idempotency_key, and result_signature receive no explanation, leaving important payment/result-signing fields opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description leads with an explicit verb and resource: 'Build a phased launch plan', then enumerates concrete deliverables (audience, positioning, channel actions, dependencies, success measures). This is specific enough to distinguish it from generic plan tools such as project_plan or business_plan_outline.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly scopes input constraints ('Uses buyer-supplied information only') and states exclusions ('no external research or outbound actions') plus the draft-for-review nature. It does not name alternative sibling tools, so it stops short of full when-to-use/when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explicitly claims 'no external research or outbound actions', which directly contradicts the openWorldHint annotation (true) that indicates potential external access. This is a serious inconsistency, so the description fails to provide reliable behavioral guidance.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose, includes price and payment authorization. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, nested objects, and no output schema, the description is insufficient. It does not explain parameter meanings, the payment flow, or what the returned draft contains. The only useful context is that it uses buyer-supplied info and returns a draft, but that's not enough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not mention any parameters, and the input schema has 0% coverage. It does not explain the meaning of input, result_expires, idempotency_key, result_signature, or payment_signature. The agent gets no help from the description in understanding how to fill these fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (assess) and resource (business facts) against a rubric, and clarifies it uses only buyer-supplied info. It does not explicitly name alternative tools, but it is clear what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context that it uses only buyer-supplied information and returns a draft, implying it is not for external research. However, it does not mention any alternative tools or explicit when-not-to-use conditions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses the exact price (0.25 USD), the requirement for explicit wallet authorization, the absence of external research/outbound actions, and that the output is only a draft for human review. Because payments are inherently destructive side effects, this is consistent with destructiveHint=true rather than contradictory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences front-load the action, then state constraints, deliverable, and price. Every sentence adds information; there is no repetition of the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, non-read-only tool with nested input and no output schema, the description covers purpose, input scope, behavioral limits, output nature, and financial side effects. It is slightly incomplete in that it does not spell out the key input fields or the optional signature/idempotency parameters, but the schema handles structure and the generic API fields are self-explanatory.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must supply parameter meaning, but it only loosely references 'business/site information' and the wallet/payment context. It does not explain what 'brief' vs 'source_text' vs 'audience' should contain, nor the role of result_expires, idempotency_key, result_signature, or payment_signature beyond generic wallet authorization.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific action ('create a prioritized local SEO plan'), specifies the input basis ('supplied business/site information'), and distinguishes this from siblings by emphasizing 'local SEO' and 'no live ranking claims'. An agent can separate this from seo_audit, keyword_cluster, or generic plan tools without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly scopes usage to buyer-supplied information and explicitly rules out external research and outbound actions, telling an agent when not to expect live data or active publishing. It does not name an alternative sibling for cases needing live ranking analysis or external research, so it misses the explicit exclusion that would earn a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds meaningful behavioral context beyond the annotations: the 0.01 USD price, explicit wallet authorization requirement, preservation of inline Markdown, and fenced-code exclusion. The destructiveHint annotation is explained by the paid, wallet-authorized nature of the call, so there is no direct contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four concise sentences with the core function front-loaded. The price and wallet-authorization warning are necessary given the non-read-only, paid nature of the tool, and there is no filler or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The core extraction semantics are present, but the tool has no output schema, zero parameter descriptions, and payment/signature infrastructure that is never mapped to actual parameters. An agent cannot determine how to authorize payment, how to set signatures, or what the result envelope looks like, so the definition is incomplete for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description needs to compensate for the five parameters. It only clarifies the core markdown input and vaguely mentions wallet authorization; result_expires, idempotency_key, result_signature, and payment_signature are left unexplained, which is insufficient for constructing a correct paid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: 'Extract ATX headings with levels and source line numbers from Markdown.' It also states exclusions (fenced code blocks) and unsupported heading types, which clearly distinguishes it from the many content-generation and text-utility siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly delimits when the tool applies: it handles ATX headings, ignores fenced code blocks, leaves inline Markdown intact, and explicitly excludes Setext and container-nested headings. It does not name an alternative tool or phrase the conditions as 'use this when...', so it stops just short of full usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotation openWorldHint=true by stating 'no external research or outbound actions.' Additionally, destructiveHint=true is not explained; the description says it 'returns a draft,' which suggests non-destructive behavior, yet the annotation implies side effects. The payment requirement is disclosed, but the core contradiction with annotations is a serious transparency failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action and output, then key constraints and payment details. No fluff or redundancy. The structure is efficient and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with five parameters, a nested input object, and no output schema, yet the description is minimal. It doesn't explain the output format beyond 'draft for human review,' nor does it detail how the payment flow works, how to use the result signature, or what the idempotency key is for. The description is insufficient for safe and correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate for parameter documentation. It only vaguely references 'supplied market evidence' (likely source_text) and mentions payment, but it fails to explain the purpose of brief, audience, result_expires, idempotency_key, result_signature, or payment_signature. This leaves the agent unable to correctly populate the input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Synthesize'), a clear resource ('supplied market evidence'), and concrete outputs ('trends, constraints, opportunities, and source-linked uncertainties'). It also distinguishes itself by explicitly limiting to buyer-supplied information, which separates it from research-oriented siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the correct usage context: use when you have supplied market evidence and want a synthesized report. It also excludes external research, which clarifies when not to use it (e.g., when outbound research is needed). However, it doesn't name alternative tools or explicitly state when to choose this over a generic document summary or executive brief.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations mark the tool as openWorldHint=true, yet the description asserts 'Uses buyer-supplied information only; no external research or outbound actions.' This directly conflicts with the annotation's implication that the tool may access or affect the outside world. The payment disclosure is helpful, but the contradiction requires a score of 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is five short, purposeful sentences that front-load the core outcome, then add constraints, return behavior, price, and wallet authorization. Each sentence carries distinct information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no parameter descriptions, the description must carry more weight. It covers the deliverable and payment model but omits return format, how optional parameters affect behavior, and how signatures/expiry fit into invocation. This is not enough for an agent to confidently call a five-parameter paid tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0 percent, and the description never explains the required `brief`/`source_text`, optional `audience`, or the signature/expiry/idempotency parameters. The high-level statement 'buyer-supplied information only' gives some context but does not compensate for the absent parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific deliverable and verb ('Create a timed, outcome-oriented agenda') and enumerates concrete components: preparation, decisions, participants, and follow-up ownership. This makes the tool's purpose clear and distinguishes it from generic copy or brief-generation siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context: the tool uses buyer-supplied information only, returns a draft for human review, and explicitly rules out external research or outbound actions. It does not name a sibling alternative such as meeting_brief or spell out comprehensive when-not-to-use cases, so it falls just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses no external research/outreach, the draft-for-review nature of the result, and the $0.25 price with explicit wallet authorization. This adds important context around the destructiveHint and openWorldHint annotations; the wallet payment is the disclosed open-world interaction, so there is no plain contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three tight sentences: core function, constraints and output mode, then pricing/payment authorization. Every sentence adds necessary decision-relevant information with no boilerplate or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

It covers the main safety and payment context and states the return mode, which is useful for a 5-parameter nested tool with no output schema. However, it leaves the relationship between required `brief` and `source_text`, the role of `audience`, and the purpose of the optional signature fields unexplained, so an agent can invoke it but without full confidence about all inputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, but it does not explain how inputs map to fields: what belongs in `brief` versus `source_text`, how `audience` is used, or what the signature/expiry/idempotency meta-parameters mean. The phrase 'supplied background...' hints at content but does not document the parameters themselves.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource—'Produce a meeting brief'—and enumerates the key sections: background, desired outcomes, agenda, questions, and likely objections. This is clearly differentiated from generic siblings by its focus on a comprehensive meeting brief, though it does not explicitly name alternative tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context: the tool is for drafting from buyer-supplied information, excludes external research and outbound actions, and returns a draft for human review. This is enough for an agent to decide when it applies, even though it does not formally list alternatives or a when-not-to-use comparison.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotations: it claims 'no external research or outbound actions' while openWorldHint is trueDM. It also describes a harmless draft output while destructiveHint is true, though it does partially address side effects with payment/wallet authorization. This is a serious behavioral mismatch.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, front-loaded with the core function, and each sentence adds a distinct piece of information: function, input constraint, output nature, and payment. It could combine the price and authorization statements, but it is still disciplined and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is incomplete for a paid tool with five parameterschers, a nested input object, and no output schema. It does not explain the purpose of the opaque signature/idempotency parameters, what 'draft for human review' means in terms of returned structure, or how the payment flow works beyond wallet authorization. An agent would struggle to invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds almost no meaning to the parameters. It vaguely refers to 'supplied page facts' but never explains brief, source_text, audience, result_expires, idempotency_key, result_signature, or payment_signature. The description does not compensate for the schema's lack of documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Generate') and a specific resource ('page titles and descriptions from supplied page facts'), and it adds output details ('character counts and intent notes'). It clearly differentiates from research-heavy services with the explicit constraint that only buyer-supplied information is used.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance about when to choose this tool over alternatives, and it never names or distinguishes sibling services. The 'no external research' constraint implies an input boundary, but it does not explain when an agent should prefer metadata_rewrite over other content-generation services.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description usefully adds price, wallet authorization, and human-review behavior beyond the annotations. However, it directly contradicts the openWorldHint annotation: annotations signal possible access/effects outside the provided context, while the description says it uses buyer-supplied information only and performs no external research or outbound actions. Per the rubric, this is an annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, each with a distinct purpose: output components, input constraint, return behavior, and pricing/payment. The most decision-relevant content is front-loaded, and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides a useful output inventory and payment context, but there is no output schema and the nested input fields are undocumented. An agent can tell what the tool broadly does, but it would still have to guess how wallet authorization maps to payment_signature and how the buyer-supplied material maps to the input schema fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it does not explain brief, audience, source_text, payment_signature, idempotency_key, result_expires, or result_signature. It only vaguely indicates that content comes from the buyer and that payment requires authorization, which is not enough to make the parameters self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb, 'Produce', and names the exact deliverable components: subject, preview text, editorial introduction, sections, and a single call to action. This makes the tool's purpose concrete and distinguishes it enough from sibling draft tools like blog_draft or outreach_email_draft.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives useful context: it uses only buyer-supplied information, performs no external research, takes no outbound actions, and returns a draft for human review. However, it never explicitly states when to choose this over a sibling or names an alternative, so usage routing is mostly implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.