Xero

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

Annotations already provide read-only, idempotent, non-destructive hints. The description adds value by detailing return format ('per-model {score, confidence, signals, raw_response} + a combined view'), default model (Workers AI Llama-3.3-70b), and payment model for Anthropic (BYO key). No contradictions 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 concise, with four sentences that front-load the primary action and key details. Every sentence adds value: purpose, default behavior, return format, and use cases. 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 no output schema, the description adequately explains the return format and covers all parameters. It mentions the default model, optional parameters, and use cases. Minor gap: does not explain scoring algorithm or confidence metric, but not critical for tool 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 100%, so baseline is 3. The description enhances understanding by explaining the default model and that `_apiKey` is required for Anthropic, and clarifies the `models` parameter values ('workers-ai', 'anthropic'). It adds meaningful context beyond the schema descriptions.

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?

Description clearly states the tool's purpose: 'Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model.' It specifies the verb 'probe' and the resource 'LLMs', and distinguishes from siblings by focusing on AI visibility scoring across multiple models, unlike similar tools like ask_pipeworx or entity_profile.

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 explicit use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also explains the default model and optional Anthropic key. However, it does not explicitly state when not to use this tool or directly compare to sibling alternatives like scan_competitor_ai_presence, so it lacks full exclusion 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 indicate safe, read-only, idempotent behavior. The description adds valuable context: routing across 3,668 tools, argument filling, and returning structured answers with citation URIs. No contradictions.

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 single paragraph of about 100 words. It is front-loaded with a priority instruction and covers key aspects. It could be slightly more concise, but it efficiently communicates the tool's purpose and usage.

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 as a router, the description covers its function, when to use, and what it returns. It does not detail failure modes, but the combination of schema, annotations, and description provides adequate completeness for an AI agent.

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 100% with all parameters described as aliases for 'question'. The description adds value by providing concrete example questions (e.g., 'current US unemployment rate'), enriching the parameter's semantics beyond the schema's generic 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 clearly states the tool answers factual questions using structured data from multiple sources, routes to appropriate sub-tools, and returns citations. It distinguishes itself from siblings by being the general routing tool, explicitly preferring it over web search, and providing a comprehensive list of use cases.

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 explicit guidance on when to use the tool: 'PREFER OVER WEB SEARCH' and a list of query types. It gives concrete examples. However, it does not explicitly exclude cases or compare with the sibling 'ask_pipeworx_grounded', which slightly reduces clarity.

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 annotations (readOnly, idempotent, non-destructive), the description adds context: it costs an extra LLM call, returns specific structured response with refusal reasons, and explains the routing mechanism. No contradictions 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?

Each sentence earns its place, front-loaded with the core purpose, and structured clearly despite the complexity. Appropriate length for the tool's nuance.

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 complexity (thousands of tools, high-stakes use) and lack of output schema, the description fully covers return format, refusal reasons, and cost trade-offs, making it 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 coverage is 100% with all parameters documented. Description adds no new meaning to individual parameters beyond what the schema provides, scoring baseline 3.

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 'Hallucination-resistant answer mode for high-stakes reads' and explicitly distinguishes from ask_pipeworx, making the specific verb+resource+scope clear.

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?

Explicitly advises to use when an answer will be quoted/cited/acted on and for high-stakes domains, and to prefer ask_pipeworx for casual lookups, providing clear when-to-use and 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?

Beyond annotations (readOnlyHint, etc.), the description details behavior: resolving market, classifying, fan-out to data packs, returning evidence and comparison, resolver contract with confidence levels, parent event extraction, fallback mechanisms, and safety short-circuits for low-confidence matches and closed markets.

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?

While comprehensive, the description is a large unbroken block of text. It contains valuable details but could be more structured with sections or bullet points for easier scanning. Every sentence adds value, but the length impacts conciseness.

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, the description fully compensates by describing response shapes (market, analysis, evidence), resolver contract, parent event extractor, news fields, and safety behaviors. Covers edge cases like low-confidence matches, closed markets, and wide spreads.

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 describes all 3 parameters (market, depth, include_raw) with examples and enums. The description adds significant context: market accepts slug/URL/question text, depth controls fan-out size, include_raw governs response size and detail. Schema coverage is 100% and the description enriches meaning.

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 'Research' and resource 'Polymarket bet', and distinguishes from sibling tools like polymarket_edges by specifying it pulls Pipeworx data. The first sentence alone captures the core 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?

Explicitly states when to use: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' Provides numerous examples of classifiers and fan-out patterns, giving clear guidance on applicability.

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 safe, idempotent, read-only behavior. The description adds value by detailing data sources (SEC EDGAR, FAERS), handling of off-calendar fiscal years, and the return format (paired data with citation URIs). No contradictions 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 a single paragraph but is front-loaded with example queries and packs essential information efficiently. It could be slightly more structured (e.g., separating company and drug details), but it remains concise and informative 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?

Given the tool's complexity (two entity types with distinct data sources), the description covers data sources, metrics, sorting, and citations. No output schema exists, but the description mentions 'paired data + citation URIs', which is sufficient for an AI agent. Minor gap: the exact structure of the comparison output is not detailed.

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 100%, but the description adds significant context: for the 'type' parameter, it explains what data each enum value pulls (financials vs adverse-event counts); for 'values', it provides examples and constraints. This enhances understanding beyond the schema descriptions.

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's purpose: side-by-side comparison of 2–5 companies or drugs in a single parallel call. It provides example queries ('Compare X and Y', 'X vs Y', etc.) and explicitly distinguishes from sequential single-pack lookups, making it highly specific 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 strongly advises to always prefer this tool over sequential lookups when comparing entities. However, it does not explicitly name sibling tools like 'entity_profile' as alternatives for single-entity lookups, which would strengthen guidance. Still, the context is clear and actionable.

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=true, idempotentHint=true, destructiveHint=false. The description adds that the tool returns 'top-N most relevant tools with names, descriptions, and full input schemas (with curated examples)', providing behavioral context beyond annotations. No contradictions.

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 relatively long but well-structured: it starts with core purpose, then usage guidance, then return value details. Every sentence adds value, though slight trimming could improve conciseness. No 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?

Given the tool's discovery purpose and absence of an output schema, the description fully explains what the output contains: 'names, descriptions, and full input schemas (with curated examples)', including limit defaults. No missing critical information.

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 100%, so the baseline is 3. The description adds value by listing available aliases (q, task, search, description) and providing examples of query values. It also explains the purpose of the query parameter and the limit, going beyond schema definitions.

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's purpose: 'Find tools by describing the data or task.' It uses a specific verb-resource pair and distinguishes itself from siblings, which are domain-specific tools (e.g., bet_research, entity_profile) rather than discovery 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 provides clear guidance on when to use: 'Use when you need to browse, search, look up, or discover what tools exist for: [list]' and explicitly advises to 'Call this FIRST when you have many tools available.' It does not explicitly mention when not to use, but the context is sufficient.

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 annotations (readOnly, openWorld, idempotent), the description details cross-source fan-out across SEC EDGAR, XBRL, USPTO, news, GLEIF and notes that patents soft-fail due to USPTO API sunset. It also discloses that names are not supported.

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 single paragraph that is dense but informative. It is front-loaded with examples and key guidance. Could be slightly more structured but is still efficient for the amount of information conveyed.

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 no output schema, the description thoroughly lists return fields (cik, filings, fundamentals, patents, news, LEI) and mentions constraints like patent soft-fail and name unsupported. For a complex tool with multiple sources, this provides sufficient 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 coverage is 100%, but description adds crucial context: the value parameter expects 'Ticker (e.g., "AAPL") or zero-padded CIK (e.g., "0000320193")' and clarifies names are not supported. The type parameter is explained as only 'company' supported with person/place coming soon.

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 explicitly states 'full cross-source profile of a US public company in ONE parallel call' and provides example queries like 'tell me about X' or 'research Acme'. It clearly distinguishes from sibling tools like resolve_entity by stating that names are not supported.

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 explicitly says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view' and provides directions for when to use resolve_entity instead for name resolution. This gives clear when-to-use and 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?

Annotations already provide destructiveHint=true and readOnlyHint=false. Description adds context about clearing sensitive data, which is useful beyond annotations. 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?

Two sentences, no wasted words, clear and front-loaded with action. Efficiently covers purpose, usage, and context.

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?

Tool is simple with one required parameter. Description covers purpose, usage guidelines, and pairing with siblings. No output schema needed; annotations handle behavioral traits. Fully adequate.

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?

Only one parameter 'key' with schema description 'Memory key to delete'. Schema coverage is 100%, so baseline is 3. Description does not add further details like format or source of keys.

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?

Description clearly states 'Delete a previously stored memory by key' with a specific verb and resource. Distinguishes from sibling tools 'remember' and 'recall' by being the deletion counterpart.

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?

Explicitly states when to use: 'when context is stale, the task is done, or you want to clear sensitive data' and suggests pairing with 'remember and recall', providing clear usage context and 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?

Annotations indicate readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral detail: 'Fetches the page, extracts title/description/key links, and emits standard llms.txt markdown format', which is consistent and provides beyond-annotation context. 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: main action, process, use cases. It is well-structured, front-loaded, and every sentence adds value. No extraneous content.

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, the description explains the output format ('single text blob ready to drop at site-root/llms.txt'). Parameters are well-documented via schema. The tool is low complexity, and the description provides sufficient context for an AI agent to understand input, output, and 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 coverage is 100% with both parameters described. The description repeats 'default 25, max 50' already in the schema for max_links, adding no additional meaning. Baseline score of 3 is appropriate.

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 a production-ready llms.txt file for any URL, specifying the verb 'generate', the resource 'llms.txt file', and the context for AI crawlers. It distinguishes itself from siblings, none of which have a similar 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?

The description explicitly lists three use cases (getting a client's site indexed, drafting for own project, auditing competitor) and implies context for when to use it. It does not mention when not to use or alternatives, but the sibling set is diverse, so non-usage is clear.

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 the tool as read-only, idempotent, and non-destructive. The description adds no new behavioral traits beyond stating it returns structured report data, but does not mention authorization needs or rate limits. With strong annotations, a score of 3 is appropriate.

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, using only two sentences. The first sentence covers purpose and scope; the second covers return structure and use case. Every word adds value with no 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?

Despite lacking an output schema, the description adequately explains the return structure (report name, date, rows covering revenue, expenses, net profit). With three optional parameters and clear annotations, the description is sufficiently complete for a straightforward financial report 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 coverage is 100%, so the baseline is 3. The description mentions 'optional date range' but does not add parameter-specific details like format nuances or behavior when omitted. The schema already provides sufficient descriptions.

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 retrieves a Profit and Loss financial report from Xero, with optional date range. It specifies the resource (income statement), verb (Get), and scope (financial reporting), distinguishing it from sibling tools like list_accounts or list_invoices.

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 indicates the tool is for financial reporting and bookkeeping analysis, which provides clear usage context. However, it does not explicitly mention when not to use it or suggest alternative tools for other financial reports, so it slightly lacks exclusion 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 readOnlyHint=true, etc. The description adds return field details and usage context but no additional behavioral traits (e.g., pagination, rate limits). 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?

Two concise sentences front-load the action and return details without unnecessary 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?

For a simple list tool with one optional parameter and no output schema, the description covers purpose and return structure. Minor gap: no mention of pagination or volume limits, but likely acceptable.

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 100% with clear parameter description. The tool description does not add extra semantic meaning beyond the schema, so baseline 3 is appropriate.

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 'List the chart of accounts' with return fields (code, name, type, class, status) and usage context. It distinguishes from sibling list tools like list_contacts or list_invoices.

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 mentions 'Use to understand an organisation's general ledger structure' but does not explicitly compare to siblings like get_profit_and_loss 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds behavioral details like pagination support and Xero filter expressions, adding 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?

Two sentences, front-loaded with purpose and return fields, then usage and features. Every sentence earns its place with no 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?

Specifies output fields and mentions pagination/filtering, compensating for lack of output schema. Sufficient for a read-only list tool with strong 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 has 100% coverage with detailed descriptions for all three parameters. Description reinforces pagination and filtering but adds no new parameter-specific meaning.

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?

Description clearly states it lists contacts (customers and suppliers) from Xero, specifying returned fields (name, email, status, flags) and usage context. It distinguishes from siblings like list_accounts and list_invoices.

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?

Explicitly states use cases: accounting, bookkeeping, accounts-receivable/payable workflows. Though it doesn't list when not to use, the context is clear and no sibling provides the same function.

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 return field details and states support for filtering and pagination. Annotations already indicate read-only, idempotent, non-destructive behavior, so the description complements without 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?

Two sentences with no fluff: first defines the action and output, second gives context and capabilities. Well-structured and 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 purpose, returned fields, filtering, pagination, and tenant selection. Lacks error handling details but is sufficient for a simple list tool with strong 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?

All three parameters are fully described in the schema. The description mentions pagination and filtering but does not add new meaning beyond the schema's existing descriptions.

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 it lists invoices and bills from Xero, with specific return fields. It distinguishes from sibling tools like list_accounts and list_contacts by focusing on invoice-specific data.

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 mentions use cases (bookkeeping, AR/AP review) and references tenant_id from list_organisations, but lacks explicit 'when not to use' or direct comparison to other invoice-listing tools if they exist.

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 readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds crucial workflow context about multi-tenancy and the need to use this tool first, enhancing transparency beyond annotations without 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?

Two sentences with no wasted words. Front-loaded with the core action ('List the Xero organisations') and supplies necessary context (multi-tenancy, workflow) 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?

Despite no output schema, the description clearly states the return fields (tenant id, name, type) and the tool's role. Combined with rich annotations, it provides complete context for a simple listing 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?

No parameters exist, and schema coverage is 100%. Per guidelines, baseline is 4. Description adds no parameter details as none are needed, but it does imply the tool is parameterless by listing the output 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?

Description specifies it lists Xero organisations (tenants) with tenant id, name, and type, clearly distinguishing its role from sibling accounting tools. It uses specific verbs ('List', 'discover') and resource ('organisations'), making the 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?

Explicitly states 'use this first to discover the tenant_id' and then pass it to other tools, providing clear when-to-use context and integration guidance. This differentiates it from siblings and establishes a necessary workflow.

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 readOnlyHint=true and destructiveHint=false, signaling safe read operation. The description adds transparency by listing returned fields (id, type, params, etc.) and noting default behavior (active only, with optional include_inactive). 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?

Two sentences with no wasted words. First sentence conveys purpose and output, second sentence gives usage guidance. Ideal front-loading.

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 simple tool (one optional param, no output schema, and comprehensive annotations), the description is sufficiently complete. It covers purpose, return structure, usage timing, and parameter effect.

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 single parameter 'include_inactive' is fully described in the schema (100% coverage). The description mentions 'active subscriptions' aligning with the default false, but adds minimal new meaning beyond the schema. Baseline 3 applies.

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 'List', the resource 'subscriptions', and specifies scope as 'the caller's active subscriptions'. It distinguishes from siblings like subscribe, unsubscribe, and other list tools by focusing on subscriptions and mentioning return fields.

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 usage scenarios: 'review what you're monitoring before adding more' and 'find an id to cancel'. This gives clear guidance on when to use the tool, though it does not explicitly state when not to use it or compare to 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?

Beyond annotations (which show non-readOnly, non-destructive), the description discloses rate limits (5 per identifier per day), cost (free, no quota impact), and expected handling (team reads digests daily, affects roadmap). 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 a single paragraph that front-loads purpose and usage, then efficiently covers behavioral and formatting guidelines. Every sentence provides necessary information without repetition 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?

For a feedback tool with no output schema, the description comprehensively covers purpose, usage triggers, message content guidelines, rate limits, and impact. All three parameters are fully described in the schema, and the description adds meaningful context without gaps.

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?

All parameters are described in the schema (100% coverage). The description adds value beyond the schema by specifying the level of detail needed in the message (be specific, which tool, what error) and reinforces the enum meanings for type. Context parameter is adequately described as optional structured context.

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 begins with a clear, specific verb phrase ('Tell the Pipeworx team something is broken, missing, or needs to exist') and enumerates distinct use cases (bug, feature, data_gap, praise). It differentiates from siblings by providing explicit triggers for when to use this tool versus others in the catalog.

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 states when to use the tool for each feedback type and what to avoid ('don't paste the end-user's prompt'). It also advises describing issues in terms of Pipeworx tools/packs, providing clear context for 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds value by stating the data source (CF analytics-engine), no PII, and caching behavior (5min-1h). This supplements the annotations well.

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: clear opening sentence, bullet points for use cases, and additional context about data derivation and caching. 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 that there is no output schema, the description sufficiently explains what is returned (top tools, top packs, total call volume) and notes caching. This is complete for a simple read-only 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 coverage is 100% with a single parameter that already has a description in the schema. The tool description does not add significant new semantics beyond restating window options. Baseline 3 is appropriate.

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 top tools, top packs, and total call volume over a window. It lists three specific use cases, making the purpose unmistakable and distinguishing it from siblings like discover_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 provides three explicit use cases with bullet points, guiding when to use the tool. However, it lacks explicit 'when not to use' guidance or alternatives, so it scores 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds valuable behavioral context: requires exactly one parameter, internal logic (Jaccard similarity threshold, partition filter for placeholder slugs), and response structure. This goes 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 well-structured with clear sections for each mode and key details in bold. It is verbose but each sentence adds value; no redundancy. It could be slightly more concise, but front-loads the critical requirement.

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 (two modes, arbitrage logic, partition checks, similarity thresholds), the description covers essential information including edge cases (placeholder filtering, low similarity). No output schema exists, but the response fields are outlined. Adequate for an AI agent.

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 100%. The description adds considerable value by explaining the difference between event and topic modes, providing examples of valid inputs, and clarifying the behavior when only one is required. It also details the implications of each parameter.

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 finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes two modes (event and topic) with specific examples, making it distinct from siblings like polymarket_edges and polymarket_kalshi_spread.

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 states when to use each mode (event for specific markets, topic for cross-event scanning) and provides example inputs. It notes that calling with no args fails. However, it does not compare usage to sibling tools, which would be helpful for differentiation.

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 extensively discloses behavioral traits: response structure (by_segment, fed candidates, diagnostics), caching behavior (1h KV cache), slippage assumptions, the fact that Fed bets are excluded from ranking, and edge calculations. Annotations already mark readOnly, idempotent, non-destructive; the description adds rich detail without 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 verbose and contains many technical details in a single paragraph, making it less concise than ideal. However, it is well-structured: it begins with a summary, then details each segment, tradeable-edge knobs, response top-level, and caching. The organization aids readability despite 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?

Given the complexity (9 parameters, no output schema, nested response structure), the description is remarkably complete. It covers input parameters, response structure (including diagnostics for empty results), caching, edge cases (Fed bets, filter skips), and usage constraints. No critical information is omitted.

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 100%, but the description adds significant value by explaining the logic behind min_kelly (half-Kelly fraction), min_edge_pp (net of slippage), slippage_pp (assumptions and note about bid/ask), category_filter (restriction to segments), and min_partition_leg_kelly (why min_kelly doesn't apply to partition arbs). This context is beyond what the schema alone provides.

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 scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price, explicitly built for 'what should I bet on today'. This distinguishes it from sibling arbitrage tools by focusing on model-based disagreement rather than cross-platform price differences.

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 the tool (discover betting opportunities based on model-driven, structural arbitrage, or concentrated longshots) and details about tradeable-edge knobs for filtering. However, it does not explicitly state when not to use or provide direct comparisons to sibling tools like polymarket_arbitrage or polymarket_kalshi_spread.

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 readOnlyHint, openWorldHint, idempotentHint, and no destructiveness. The description goes beyond by detailing safety fields (compatibility_warning, temporal_alignment, skipped_cross_type/subtype) and explaining conditions for meaningful spread calculation (e.g., aligned months). 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 well-structured with clear sections (purpose, modes, response, safety fields) but is somewhat lengthy. Minor redundancy (e.g., 'pre-mapped ≠ tradeable' at end) but overall each sentence contributes to understanding.

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 lack of output schema and the complexity of the tool (cross-venue spread with compatibility checks), the description is remarkably complete. It covers the response structure, edge cases (compatibility warnings, temporal alignment mismatches), and provides realistic expectations about tradeability.

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 100% with descriptions for each parameter, but the description adds significant value by explaining the two modes, the list of topic shortcuts, and how parameters interact (e.g., overriding via explicit parameters). This enriches the schema's basic descriptions.

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 that the tool computes the cross-venue spread between Kalshi and Polymarket for the same resolving question. It specifies the two modes (topic and explicit) and explains the concept of spread, distinguishing it from sibling tools like polymarket_arbitrage by focusing on cross-venue comparison.

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 explains when to use each mode: topic for pre-mapped shortcuts and explicit for custom pairings. It warns that most pre-mapped topics return compatibility warnings and advises that real spreads are rarer, guiding the agent on realistic expectations.

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 readOnlyHint and idempotentHint. Description adds scoping detail (identifier-based) and behavior when key is omitted. No contradictions.

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?

Two sentences, front-loaded with main action, no wasted words. Efficient and clear.

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 simple tool with one optional param and good annotations, description provides necessary context: purpose, usage, scoping, and pairing with siblings.

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 covers parameter fully (100% coverage). Description reinforces but does not add new information beyond what schema already provides.

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?

Description clearly states the tool retrieves a saved value or lists keys, with specific verbs and resource. Distinguishes from siblings 'remember' and 'forget'.

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 context for when to use (look up stored context without re-deriving) and mentions pairing with remember/forget. Does not explicitly state when not to use, but 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?

Describes mark_read effect on next call results, return fields (source, citation_uri, raw payload), and idempotent nature beyond annotations (readOnlyHint, idempotentHint). No contradictions.

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?

Five sentences, each earning its place: purpose, return fields, filter options, mark_read behavior, alternative access. Front-loaded with action verb.

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, description sufficiently explains returns. Complexity level is moderate; annotations and schema are rich. No gaps left.

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 100%, but description adds real-world guidance: example type filter 'sec_8k', clarifies mark_read and since semantics, and sets limit range implicitly.

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?

Clearly states 'Pull fired events from your subscription feed' with specific verb and resource. Distinct from siblings like 'list_subscriptions' which manage subscriptions, not alerts.

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?

Advises 'Polls work fine' and notes alternative direct API endpoint for scripts/dashboards. Could explicitly exclude cases, but provides solid context.

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 (readOnlyHint, idempotentHint, etc.), the description details the tool's behavior: fans out to SEC EDGAR, GDELT→GNews fallback, USPTO with soft-fail, and returns structured changes with citation URIs. This adds significant 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 somewhat long but every sentence adds value, including example queries and fallback details. It is front-loaded with examples and clearly organized, though a slight trim could improve conciseness.

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 no output schema, the description specifies the return structure (changes[] grouped by source, total_changes, citation URIs). It covers input formats, data sources, fallback behavior, and limitations (USPTO soft-fail), leaving no major gaps.

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 100%, but the description adds valuable context: explains that 'since' accepts ISO date or relative shorthand (e.g., '7d', '30d'), gives recommended values, and clarifies that 'value' can be ticker or CIK. This enriches semantic understanding.

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 provides a change feed for a company in a specified time window, using examples like 'what's new with X'. It distinguishes itself from the sibling tool entity_profile by explicitly saying to use that for static profiles.

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 explicit examples of when to use (e.g., 'recent changes for a company') and when not to ('Use entity_profile instead when you want the static profile'). It also mentions the tool fans out to multiple sources with fallback logic, providing clear context.

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 idempotent and non-destructive; description adds session-persistence details (authenticated vs anonymous) and scoping by identifier, providing context 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?

Description is concise with clear structure, but could be slightly shorter without losing meaning; still efficient and well-organized.

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?

No output schema, but for a simple save operation, description adequately covers purpose, usage, and persistence behavior; lacks return value details but acceptable.

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 100% with clear descriptions for key and value; description confirms key-value nature but does not add significant additional meaning.

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?

Description clearly states the tool's action ('save data') and resource ('key-value pair'), and distinguishes from siblings by mentioning pairing with recall and forget.

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?

Explicitly tells when to use ('when you discover something worth carrying forward') and references alternatives (recall, forget) for retrieval and deletion.

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 (readOnlyHint, idempotentHint) already indicate safe, idempotent behavior. The description adds that each call cascades through multiple lookup endpoints internally, replacing 2-3 manual lookups. No contradictions.

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 well-structured, starting with example queries, then purpose, usage guidance, and detailed type information. Every sentence adds value, though slightly lengthy but justified by the need to explain two entity types.

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 no output schema, the description fully explains what each supported type returns, including citation URIs. It also notes the internal cascading behavior, making it complete for a resolver 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 coverage is 100%, providing baseline 3. The description adds significant meaning: explains auto-disambiguation for company, accepts multiple input formats (ticker, CIK, name), and details the returned fields (ticker, CIK, citation URI for company; RxCUI, ingredient, brand for drug).

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 resolves a user-spoken name to the canonical/official identifier required by other tools. It provides specific examples like 'ticker', 'CIK', 'RxCUI' and distinguishes from sibling tools such as entity_profile and compare_entities.

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?

Explicitly says 'Use FIRST whenever you have a name but need an ID.' It lists supported types and what they return. Does not explicitly state when not to use, but the context implies alternatives for existing IDs.

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, openWorldHint, idempotentHint, destructiveHint=false. Description adds that it probes each entity with ai_visibility_check, returns ranked list with score/confidence/signal density, and treats first entity as subject. Adds behavioral context beyond annotations without 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?

Two sentences: first states purpose and process, second gives use case and output. 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?

No output schema, but description explains return: ranked list with score, confidence, signal density. Covers high-level behavior. Mentions models and apiKey implicitly via 'probes each entity' but could elaborate on input constraints. Reasonably 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 coverage 100% sets baseline 3. Description adds that entities array must be 2-8 and first is subject, and explains context for disambiguation. Adds meaning beyond 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?

Clearly states 'Compare AI visibility across multiple entities side-by-side' with specific verb and resource. Distinguishes itself from sibling ai_visibility_check (single entity) and compare_entities (generic).

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?

Explicit use case: 'competitive AI-marketing audits'. Implies when to use vs alternatives (multi-entity comparison). Lacks explicit 'when not to use' but context is clear.

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 show readOnly=true, idempotent=true, destructive=false. The description adds valuable context: partial failures behave gracefully, bundlephobia's first measurement can take 5-30s, sources_failed lists timeouts. No contradictions.

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 relatively long but front-loaded with the core purpose. Every sentence adds value (ecosystem scope, return fields, partial failure behavior). Minor room for conciseness but effective.

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 lacking an output schema, the description enumerates the return structure (summary block fields, per-advisory detail, links, alternative versions). It covers all necessary context: what data is returned, edge cases (partial failures, timing), and scope limitations. Complete for a composite API.

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 covers both parameters with descriptions (package: npm package name, version: optional, defaults to latest). The description adds that scoped packages like @types/node are accepted and that version defaults to latest published, providing extra clarity beyond 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 composite check for npm package evaluation, naming specific services (deps.dev, bundlephobia) and the exact data returned (license, advisories, bundle size, etc.). It distinguishes itself from sibling tools, which are unrelated (business, AI, betting).

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?

Explicitly tells when to use: when an agent asks 'is X safe/popular/small' or 'what does adding lodash cost me'. Also specifies ecosystem scope (NPM only) and points to alternatives for other ecosystems (deps.dev:version). Mentions partial failures and timing caveats.

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 readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds important behavioral details: technical specs (BGE-base-en embeddings, 500-char windows, 200K char cap with truncation flag), which go 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 well-structured: first sentence states core action, followed by use-case, pairing, and technical details. Every 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?

Despite lacking an output schema, the description explains the return value (top-N passages with offsets and scores) and covers technical constraints (model, windowing, cap, truncation). This provides complete context for an agent.

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 100%, so the baseline is 3. The description restates the text cap and adds truncation flag context but does not significantly deepen meaning beyond what the schema already provides.

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 explicitly states 'Semantic search INSIDE a fetched record', uses the verb 'search' with clear resource ('a fetched record'), and distinguishes from siblings like ask_pipeworx_grounded by explaining when to use each.

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 'Use when the record is too big to cram into the prompt' and contrasts with ask_pipeworx_grounded, providing clear when-to-use and alternative 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?

Discloses behavioral traits beyond annotations: requires OAuth, returns subscription id, mentions rate limits on SMS (10/day cap), auto-disable of webhooks after 10 failures, and signing secret. 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?

Description is a single paragraph but efficient; every sentence adds value. It could benefit from bullet points for readability, but 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?

Covers all aspects: purpose, return value, prerequisites, type-specific parameters, delivery options, constraints, and rate limits. No output schema exists, but the return of subscription id is mentioned. Complete for a subscription creation 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?

Adds significant meaning beyond the 100% schema coverage: explains each type enum value with example params, details delivery subfields including webhook signing and SMS verification. Schema alone does not provide these examples or constraints.

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?

Description clearly states 'Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id.' It specifies the verb (create) and resource (subscription), and distinguishes from siblings like list_subscriptions and unsubscribe.

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 context: requires Pipeworx OAuth account, no anonymous/BYO, details supported types and delivery channels. It implicitly advises when to use (for monitoring live data events) but does not explicitly state when not to use or provide direct 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds that returns example questions with tool calls, but doesn't elaborate on edge cases or exact response format.

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?

Description is front-loaded with purpose and well-structured. Slightly verbose but every sentence adds value. Could be tightened without losing meaning.

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?

No output schema, but description fully explains return structure (category-bucketed examples with tool calls). Covers when to use, how to use, and what to expect, making it 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 has 100% coverage; description adds examples of topics and explains omitting for full spread, providing more context than the schema description 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 clearly states the tool's purpose: returning category-bucketed example questions with exact tool calls. It distinguishes itself from siblings as the onboarding entry point for new users.

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?

Explicitly advises to use this first when unfamiliar with Pipeworx, and explains how to optionally focus on a topic. Lacks explicit 'when not to use' but 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?

Beyond annotations (destructiveHint=false, idempotentHint=true), the description adds that the row is deactivated not deleted, preserving historical events. Ownership enforcement is also disclosed. No contradictions 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?

Two sentences, no unnecessary words. Front-loaded with action and resource. 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 single-parameter tool with no output schema, the description provides complete context: what it does, side effects, ownership constraints, and impact on historical data. No gaps.

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 has 100% coverage with description for the 'id' parameter. The description does not add additional semantic meaning beyond the schema. Baseline 3 is appropriate.

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?

Description clearly states it cancels a subscription by id. The tool name matches the action, and it distinguishes itself from 'subscribe' by specifying cancellation. Ownership enforcement adds specificity.

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?

Explicitly says when to use: to cancel a subscription. Ownership enforcement indicates who can use it. However, it does not explicitly state alternatives or conditions when not to use, but that is clear from context.

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 provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds detail about the return format (verdict, structured form, citation, percent delta) and mentions it v1 supports only company-financial claims, which is important behavioral context beyond 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 front-loaded with the core purpose and includes multiple relevant details. While slightly verbose, every sentence adds value. It efficiently conveys the tool's utility and limitations.

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 no output schema, the description explains the return values and the domain limitation. Given the tool's complexity, the description covers the essential aspects for an agent to use it correctly, though it could mention error scenarios or output format nuances.

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 100% with a single parameter 'claim' already described. The description adds examples and domain context, but these do not significantly enhance understanding of the parameter itself beyond what the schema provides. Baseline 3 is appropriate.

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 specific verb phrases like 'fact check' and 'verify the claim that...' and clearly states the tool's function: natural-language claim verification against authoritative sources. It distinguishes itself from siblings by specifying the domain (company-financial claims) and noting it replaces multiple sequential calls.

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 'Use whenever the agent needs to check whether something a user said is factually correct,' providing clear context. It does not explicitly list when not to use or compare to specific alternatives, but the domain limitation and examples provide implicit guidance.

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