Greenhouse

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by detailing default model (free Workers AI), Anthropic BYO key model, user payment responsibility, and return structure (per-model {score, confidence, signals, raw_response} + combined view). 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?

Single paragraph, front-loads the main action and return format, includes essential details without fluff. 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?

Despite no output schema, the description adequately explains return structure. Covers purpose, usage, model behavior, and practical use cases. With 4 parameters and simple types, this is complete enough for an agent to invoke 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 coverage is 100%, but the description adds meaning beyond schema: explains which models are available (workers-ai free, anthropic requires _apiKey), clarifies that _apiKey is passed through to api.anthropic.com, and states context helps disambiguate names. This significantly aids agent 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 it probes LLMs for knowledge and scores visibility, with a specific verb ('probe') and resource ('LLMs', 'visibility score'). It distinguishes from siblings by focusing on AI visibility audits, which is unique among the listed 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 use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') but does not directly differentiate from similar siblings like 'scan_competitor_ai_presence' or state when not to use.

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, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds that it routes to one of 3,547 tools, fills arguments, and returns structured answers with citation URIs. This provides useful behavioral 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?

The description is front-loaded with the key directive 'PREFER OVER WEB SEARCH' followed by detailed examples. It is slightly long but each sentence adds value, and the structure is logical.

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 mentions returned structured answers with citation URIs, which is sufficient. It covers many data sources and use cases, making it complete for a read-only query 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 all parameters aliases for 'question' and described. Description adds examples and clarifies the parameter's role in natural language. Baseline is 3 due to high coverage, but the examples and usage hints justify a 4.

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 answers factual questions about current/historical data from authoritative sources. It distinguishes itself from sibling tools by being a general router to 3,547 tools, and explicitly says 'PREFER OVER WEB SEARCH', making its purpose 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?

Provides explicit when-to-use: for factual questions about real-world entities, events, numbers, and lists many examples. It implies alternatives (web search) but does not explicitly state when not to use or specific exclusions. Clear guidance overall.

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 read-only, open-world, idempotent, non-destructive. Description adds behavioral details: returns explicit refusal reasons (not_in_source, no_tool_match, etc.), costs one extra LLM call, and extracts answer from tool result only. 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?

Description is dense but informative, front-loading the key concept. Every sentence adds value, though slightly verbose with listing all refusal reasons and aliases. Could be trimmed slightly without loss.

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 6 parameters (all aliases) and no output schema, description fully covers return format (answer, evidence, confidence, source, fetched_at, refusal_reason) and explains failure modes. No gaps given schema richness and 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 coverage is 100% with all parameters being aliases for 'question'. Description repeats what schema says ('accepts query, q, prompt, text, input as aliases'), adding no semantic value beyond 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?

Description clearly states it is a 'Hallucination-resistant answer mode for high-stakes reads' that extracts answers only from tool results, with explicit refusal fallbacks. It distinguishes from sibling ask_pipeworx by emphasizing evidence-based answering and use cases like financial verdicts or legal claims.

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 ('whenever an answer will be quoted, cited, or acted on') and when to prefer ask_pipeworx ('casual lookups'). Mentions extra LLM cost, providing clear trade-offs.

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 extensive behavioral details: low-confidence matches suppress analysis, closed markets skip fan-out, wide spreads carry tradeability notes, and resolver contract warnings. 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 very long and dense, containing multiple paragraphs of classifiers, fan-out examples, and response shapes. While informative, it lacks conciseness and could be shortened without losing key points.

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 explains return values (result.market, result.analysis, result.evidence, resolver contract, parent event extractor, news fields, safety mechanisms). It covers all aspects needed 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 100%, so baseline is 3. The description adds extra context for each parameter, such as explaining quick vs thorough fan-out and the impact of include_raw on response size. It also provides examples in the schema itself.

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-resource pair ('Research a Polymarket bet') and lists clear use cases ('should I bet on X', 'what does the data say about Y'). It distinguishes from sibling tools like polymarket_arbitrage and polymarket_edges by focusing on single-bet research with data fan-out.

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 usage scenarios are provided ('Use for...'), and the description implies when to use this tool over siblings. However, it does not explicitly state when not to use it or name alternatives, leaving some ambiguity.

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 behavioral context beyond annotations: explains data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handling of off-calendar fiscal years, sorted results, and citation URIs. Annotations already declare read-only, open-world, idempotent, non-destructive; 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?

Front-loaded with key information (use cases, preference). All sentences contribute: covers purpose, data sources, behavior, output. Slightly long but efficient; no redundancy. Could trim 'Results sorted...' to one sentence, but overall 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?

Given no output schema, the description adequately describes return values (paired data + citation URIs) and sorting. Covers both entity types thoroughly. No missing critical details for a comparison tool with two simple 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 provides 100% coverage (type enum, values array constraints). Description adds meaning: specifies what data each 'type' retrieves (company: latest 10-K metrics; drug: adverse events, approvals, trials) and gives examples (tickers/CIKs for companies, drug names). This is beyond the schema's minimal 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?

Tool name and description clearly indicate side-by-side comparison of 2–5 entities. Description enumerates specific use-case phrases like 'Compare X and Y', 'X vs Y', 'which is bigger', and explicitly contrasts with sequential lookups, making 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 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and provides concrete example queries. Lacks explicit 'when not to use' statements, but the preference is strong enough for an AI agent to apply 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?

Annotations already indicate safe, idempotent, non-destructive behavior. Description adds that results include full schemas ready to call, no second lookup needed—useful behavioral insight 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 well-structured, front-loaded with purpose, but includes a long list of domains that could be condensed. Still, every sentence serves a purpose.

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 role as a discoverer, the description adequately explains inputs (query, limit), output (top-N tools with schemas), and context (call first). No output schema needed as description covers return content.

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?

Input schema has 100% coverage, describing all parameters including aliases. Description reiterates that query accepts natural language but adds no new meaning beyond schema details.

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 finds tools by describing a task or data domain, listing many specific domains. It distinguishes from sibling tools (specific data tools) by being a meta-tool for discovery.

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 'Call this FIRST when you have many tools available and want to see the option set'. Provides clear context but doesn't explicitly 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, idempotentHint, openWorldHint, destructiveHint. The description adds context about fanning out across multiple sources and the potential soft-failure of patents API, which adds value 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 a single dense paragraph, but it efficiently packs a lot of information without unnecessary words. It could be slightly improved with structure, but it's still appropriate.

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 high complexity, the description thoroughly explains return fields (cik, filings with URIs, fundamentals, patents, news, LEI) and addresses limitations (patents API sunset). It provides a complete picture.

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 repeats some parameter info but adds examples (e.g., zero-padded CIK). It does not significantly enhance beyond the 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 tool provides a full cross-source profile of US public companies in one call, listing specific sources and outputs. It distinguishes itself from siblings like resolve_entity by indicating it does not support names.

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 usage examples and states it should be preferred over chaining single-pack lookups for holistic views. It also tells when not to use: names not supported, use resolve_entity first.

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 cover destructive and idempotent hints. Description adds use-case context but does not clarify behavior for non-existent keys or other edge behaviors.

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, direct and efficient, front-loading the action.

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 one-parameter tool with no output schema, the description covers purpose, usage, and sibling pairing adequately.

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 baseline 3. Description adds no extra meaning beyond the schema's 'Memory key to delete'.

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 specific verb and resource, and distinguishes from siblings 'remember' and 'recall'.

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'. Also hints at pairing with siblings, though no explicit when-not-to-use.

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, destructiveHint=false, and idempotentHint=true, which align with the description's mention of fetching and extracting without modification. The description adds behavioral details (fetches page, extracts title/description/key links, outputs text blob) beyond annotations, but doesn't cover rate limits or auth. Overall, good transparency 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 concise with two sentences and a bulleted use-case list. It front-loads the purpose and outcome, and every sentence adds value without repetition or fluff.

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 two-parameter tool with no output schema, the description fully covers what the tool does, its result (a text blob), and its use cases. Annotations handle safety. No gaps remain.

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 descriptions already explain both parameters clearly (url, max_links with defaults). The description reinforces these by mentioning extracted elements and output format but doesn't add significant meaning beyond the schema. With 100% schema coverage, 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 generates a production-ready llms.txt file for any URL, specifying the verb 'generate', resource 'llms.txt file', and target 'any URL'. It differentiates from siblings by its specific function, which is unique among the listed 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 explicit use cases: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing competitor sites. While it doesn't state when not to use it or name alternatives, the sibling list has no close equivalents, so this 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?

Annotations already provide safety profile (readOnlyHint, idempotentHint, destructiveHint). Description adds return-content detail but lacks deeper behavioral disclosures like rate limits or authentication nuances.

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?

Single concise sentence that front-loads purpose and immediately lists return contents. 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 low complexity, full schema coverage, and presence of output schema, the description adequately covers what the tool returns and its purpose.

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 both parameters. Description adds no additional parameter-level meaning beyond referencing 'by ID'.

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?

Specific verb 'Get', resource 'full candidate profile', and lists returned data (resume, contact info, etc.). Distinguishes clearly from sibling listing 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?

Clear when to use (by ID for full profile), but no explicit exclusions or direct comparison to sibling tools like greenhouse_list_candidates.

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 read-only, idempotent, non-destructive. Description adds some value by listing return fields but no additional behavioral context beyond 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?

Two sentences, front-loaded with purpose, no filler words. Every part 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 simple retrieval tool with full annotations and schema coverage, the description covers the main purpose and return content. Slightly lacks info on output schema details but overall 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 descriptions for both parameters. Description adds minimal extra meaning (e.g., 'by ID' already implied). Baseline score 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 uses specific verb 'Get' with resource 'job details by ID' and lists return fields, clearly distinguishing it from siblings like greenhouse_list_jobs or greenhouse_get_candidate.

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?

Implied usage: use when you need full details of a specific job. No explicit when-not or alternatives mentioned, though sibling tool greenhouse_list_jobs exists for listing.

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, idempotentHint, openWorldHint, and destructiveHint=false. The description adds that it returns applicant names, job IDs, status, and dates, and supports filtering. This provides some behavioral context beyond annotations, but does not disclose pagination behavior, rate limits, or data freshness. With strong annotation coverage, a 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?

Two concise sentences: first states purpose and return fields, second describes filtering. Every word earns its place. No redundancy, no fluff. Front-loaded with the core action.

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 an output schema present, the description does not need to detail return structure. It mentions key fields and filtering. However, it omits mention of pagination parameters (page, per_page) and the exact status values, which are in the schema. For a list tool, this is sufficient but not exhaustive, hence 4.

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%; each parameter has a clear description. The tool description adds a filtering hint ('by job or stage') that partly overlaps with schema descriptions. It does not clarify the mismatch between 'stage' in description and 'status' in schema. Overall, little added value beyond the schema, so 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 clearly states the tool's purpose: 'View job applications across your pipeline.' It specifies returned fields and filtering options. However, it mentions filtering by 'stage' but the schema uses 'status' with specific enum values (active, converted, hired, rejected), not general stage names like 'screening' or 'interview'. This slight inaccuracy may confuse agents but does not obscure the core function.

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?

No explicit guidance on when to use this tool versus siblings like greenhouse_list_candidates or greenhouse_get_candidate. The description only states what it does, not when to prefer it. Implicit differentiation by resource type (applications vs. candidates) is weak. No alternatives or exclusion criteria are mentioned.

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 readOnly, idempotent, non-destructive. Description adds return fields but no behavioral 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?

Two sentences with purpose upfront, no redundant information, 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?

Output schema exists, description lists key return fields, and pagination is implied via schema. Complete for a list 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 descriptions cover all parameters; description does not add additional semantics beyond what schema 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 searches candidates, specifies returned fields, and distinguishes from greenhouse_get_candidate for full details.

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 an alternative sibling tool for full details, but does not explicitly contrast with other candidate-related siblings like greenhouse_list_applications.

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 value by specifying the returned fields (titles, IDs, departments, statuses, dates), which is helpful for selecting parameters.

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, 26 words, front-loaded with purpose. No unnecessary 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?

Given the presence of output schema, annotations, and sibling tools, the description is sufficient. It could mention pagination behavior or sorting, but the included information covers the core functionality.

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 parameter descriptions, so the description does not need to explain parameters. However, it adds some context about return values, which indirectly helps parameter selection.

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 browses job postings and lists specific fields returned. It distinguishes itself from sibling greenhouse_get_job by noting that the sibling provides full details and candidate pipeline.

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?

Description provides explicit guidance to use greenhouse_get_job for full details, implying this tool is for listing summaries. While it doesn't state when not to use it, the alternative 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 provide readOnlyHint, idempotentHint, destructiveHint. Description adds details on return fields (id, type, params, etc.) and the effect of the include_inactive parameter, adding value 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?

Three sentences: action, return fields, usage guidance. Front-loaded and every sentence adds value with 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 clearly lists the return fields. Includes parameter behavior implicitly. Complete for a simple list tool with one optional parameter.

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% and already describes include_inactive. Description mentions return fields but does not add further meaning to the parameter beyond what schema provides. Baseline 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?

Clearly states 'List the caller's active subscriptions' – a specific verb (list) and resource (subscriptions). Also lists return fields, distinguishing it from sibling tools like subscribe/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?

Explicitly says 'Use this to review what you're monitoring before adding more or to find an id to cancel', providing clear context for when to use the tool. Does not explicitly state 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?

The description discloses several behavioral traits beyond the annotations: rate-limited to 5 per identifier per day, free, doesn't count against tool-call quota, team reads digests daily, signal affects roadmap. The annotations only provide hints (readOnlyHint false, etc.) but the description adds concrete operational details that an agent needs to know.

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 moderately long but well-organized: purpose first, then usage guidance, then tips, then limitations. Every sentence adds unique value. It is front-loaded with the core action ('Tell the Pipeworx team something is broken...'). A slight deduction for verbosity in the middle, but still 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?

The description is complete for a feedback tool with 3 parameters (one enum, one nested object) and no output schema. It covers purpose, categories, when to use, format of feedback, behavioral notes (rate limit, free), and even mentions how the feedback is used (roadmap impact). Nothing critical is missing.

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 baseline is 3, but the description adds meaningful context: it explains the enum values in context ('bug = something broke...'), guides message content ('Be specific, 1-2 sentences typical'), and clarifies the optional context object's fields. This goes beyond the schema's minimal 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 explicitly states the tool is for telling the Pipeworx team something is broken, missing, or needs to exist. It further clarifies by listing specific categories (bug, feature, data_gap, praise, other) and provides examples (wrong/stale data, missing tool, surprising success). This clearly distinguishes it from sibling tools which are for querying or discovery.

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 when-to-use guidance: 'Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise).' It also advises on what to include (describe in terms of tools/packs, not pasting user prompt) and notes a rate limit. It does not explicitly contrast with sibling tools but the context makes it clear this is a feedback channel.

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 read-only, open-world, idempotent, non-destructive behavior. The description adds value by explaining the source (CF analytics-engine), caching (5min-1h), and that no PII is involved.

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 every sentence provides unique value. Use cases are bulleted, and technical details are separated cleanly.

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 input schema and strong annotations, the description fully covers what the tool does, its use cases, data sources, and caching behavior. No output schema is needed as the output is explained.

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 'window' has full schema coverage and enums. The description adds context by explaining that shorter windows surface current trends and longer windows show steady-state demand.

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: returns top tools, packs, and call volume over configurable time windows. It uses specific verbs and resources, distinguishing it from siblings like 'discover_tools' and 'validate_claim'.

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 lists three concrete use cases (discovering hot data sources, confirming canonical tool, seeing alignment) but does not explicitly mention 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?

Description adds significant behavioral context beyond annotations: monotonicity checks, partition_sum checks, Jaccard similarity filter, placeholder filtering, and response structure. Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) are consistent with the described read-only analysis 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 comprehensive and well-structured with clear sections for each mode. While every sentence adds value, it is somewhat dense and lengthy, but not overly verbose. A slight trim could improve conciseness while retaining information.

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, multiple checks), the description covers all essential aspects: modes, parameter details, algorithmic steps, response fields, and edge cases. No significant gaps remain.

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 event and topic parameters. The description adds valuable meaning: explains the purpose, provides example values, warns about required at least one, and describes the behavior for each mode. This goes well beyond the 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 tool finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes two modes (event and topic) with specific use cases, making its purpose highly specific and differentiating it from 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?

Explicit guidance is provided: use event mode for a specific market, topic mode for cross-event scanning. It warns that calling with no args fails and explains the trade-offs between modes, including examples and conditions like Jaccard similarity threshold.

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, etc. The description goes far beyond, detailing the three model segments, edge calculation, Kelly sizing, diagnostics, and cache behavior. 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 very long and dense, packed with technical details. While well-organized into segments, it could be more concise 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 no output schema, the description fully explains the output structure (by_segment, diagnostics) and covers edge cases like empty segments. All necessary context for a complex tool is provided.

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 detailed parameter descriptions, and the description adds extra context for key parameters like min_liquidity, max_spread_pp, and min_partition_leg_kelly, explaining their tradeable-edge roles beyond the 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 tool scans Polymarket markets and returns opportunities where Pipeworx data disagrees with market price, explicitly for daily betting decisions. It distinguishes from sibling tools like polymarket_arbitrage by referencing Pipeworx data and the unique output segments.

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 strong usage context ('Built for what should I bet on today') and explains the tradeable-edge knobs, but does not explicitly say when not to use this tool versus alternatives like polymarket_arbitrage or bet_research.

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 extensive behavioral traits beyond annotations: compatibility_warning conditions (non-equivalent bet shapes, semantically unrelated events), temporal_alignment checks, skipped cross-type/subtype counters. No contradiction with annotations (readOnlyHint, etc.).

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?

Well-structured with sections for modes, response fields, and safety warnings. Front-loaded with purpose. Slightly verbose but every sentence adds value; could be tightened slightly but remains 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?

No output schema but description compensates with detailed response structure (leg-by-leg prices, spread array, safety fields with conditions). Covers edge cases (compatibility, temporal alignment). Complete enough for an agent to use 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 already has 100% description coverage for all 3 parameters. Description adds value by listing the 10 topic shortcuts, providing examples of explicit ticker/slug, and explaining override behavior. Meaningfully enhances 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?

Description clearly states it computes cross-venue spreads between Kalshi and Polymarket for the same resolving question, with two operational modes (topic shortcuts and explicit pairing). It distinguishes from siblings like polymarket_arbitrage by focusing on the same outcome across venues.

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-to-use guidance: topic mode for pre-mapped macro shortcuts, explicit mode for custom pairings. Warns about compatibility warnings, temporal alignment requirements, and that pre-mapped topics often aren't tradeable. Effectively tells the agent 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 indicate read-only, idempotent, non-destructive. Description adds scoping detail and listing behavior when key omitted.

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 no wasted words; 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?

Fully explains retrieval behavior, listing mode, and scoping; no output schema needed.

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 the single parameter fully. Description restates the behavior but adds no new 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?

The description clearly states the tool retrieves a stored value or lists keys, using specific verbs and distinguishing 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?

Explicitly advises when to use for looking up stored context and pairs with remember/forget, but does not explicitly state when not to use.

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 claim readOnlyHint=true, but the description reveals that setting mark_read:true modifies read status (a write operation). This contradicts the annotation, leading to a score of 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 concise, with 4 well-structured sentences. The main purpose is front-loaded, followed by details. 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?

It explains the output structure (source, citation_uri, raw payload) and mentions alternative access. However, it does not explain the unread_only parameter or limit details. With no output schema, this is a minor 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 coverage is 100%, and the description adds an example for type ('sec_8k'), explains the ISO timestamp for since, and clarifies the effect of mark_read. It does not cover unread_only or limit beyond the schema, but overall adds value.

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 'Pull fired events from your subscription feed,' using a specific verb and resource. It describes the data payload (source, citation_uri, raw event). This differentiates it from siblings like list_subscriptions.

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 that the same feed is available via an HTTP endpoint for scripts and dashboards, providing an alternative. It also notes that polls work fine, implying repeated calls are safe. However, it does not explicitly state when to avoid this tool vs. 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?

Discloses fan-out to multiple sources (SEC, GDELT/GNews, USPTO), fallback mechanism, potential patent API sunset, and return structure (changes[] grouped by source, total_changes, citation URIs), all beyond what annotations provide.

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?

Single dense paragraph but well-organized: purpose first, then sources, parameter details, then alternative tool. No wasted words, though could be broken into bullet points for readability.

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 covers input formats, behavior, sources, limitations (patent soft-fail), and return structure, making it fully sufficient for an AI agent to invoke 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?

With 100% schema coverage, baseline is 3, but the description adds meaningful context: explains `since` with relative shorthand examples, `type` restrictions, and `value` as ticker or CIK, which exceeds 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 explicitly states the tool as a 'change feed for a company' with examples like 'what's new with X', clearly distinguishing it from sibling tool entity_profile ('use entity_profile instead when you want the static 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?

Provides explicit when-to-use (recent changes) and when-not-to-use (static profile, directing to entity_profile). Also explains fallback behavior (GDELT→GNews) and parameter formats ('7d', '30d', ISO date).

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?

Description adds valuable context beyond annotations: key-value scoping by identifier, persistence differences for authenticated vs anonymous users (24 hours), and 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?

Four sentences, front-loaded with primary purpose, each sentence adds distinct value with no fluff.

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 2-parameter tool without output schema, the description fully covers purpose, usage, parameter semantics, behavioral details, and sibling relationships.

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 meaningful examples (e.g., 'subject_property', 'target_ticker') and clarifies value can be 'any text', enhancing 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 explicitly states 'Save data the agent will need to reuse later' and provides concrete examples like 'resolved ticker, target address, user preference', clearly distinguishing it from sibling tools 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?

Open with 'Use when you discover something worth carrying forward' and explicitly directs to pair with recall/forget, giving clear when-to-use and alternative 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?

Annotations already declare safe, idempotent, read-only behavior. Description adds internal cascading logic and return value details (citation URIs), 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?

Well-structured: starts with example queries, then concise action statement, then bullet-like details for each type. No wasted words; 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?

Complete for a 2-param lookup tool with no output schema. Covers input validation, output format, internal behavior, and usage context.

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 100% schema coverage, baseline is 3. Description adds significant value by specifying accepted input formats per type (ticker, CIK, name for company; brand/generic for drug) and describing output mappings.

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 resolves names to canonical identifiers, with specific examples (ticker, CIK, RxCUI) and distinguishes it as the first step for ID lookups.

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', and explains that it replaces 2-3 manual lookups. Could improve by contrasting with sibling tools like compare_entities, but still 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 readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that it probes each entity (multiple calls) and uses ai_visibility_check internally. It also mentions optional API key for Anthropic, which is useful behavioral 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?

The description is 4 sentences, front-loaded with the purpose, then explanation, use case, and output. Every sentence 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?

No output schema, but the description specifies the return format (ranked list with score, confidence, signal density). Input schema is fully covered. For a competitive analysis tool, this is adequately 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?

Input schema coverage is 100% with descriptions for all 4 parameters. The description adds extra meaning: 'models' can be omitted for just workers-ai, and 'entities' first entry is treated as subject. This goes beyond the schema's 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 'Compare AI visibility across multiple entities side-by-side', specifies it probes each entity with ai_visibility_check, ranks by score, and surfaces which is most/least recognized. It provides a concrete example and distinguishes itself from the sibling tool 'ai_visibility_check' which is for single 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?

The description explicitly says 'Useful for competitive AI-marketing audits' and gives an example query, indicating when to use. It implies that for a single entity one should use ai_visibility_check, but does not explicitly state when not to use this tool. However, 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?

Annotations indicate readOnlyHint and idempotentHint. Description adds value by explaining partial failure handling, bundlephobia's first measurement delay (5-30s), and that sources_failed will list 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?

Description is front-loaded with purpose, uses bullet-like list for return fields, and is concise yet comprehensive. 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?

Without output schema, description fully documents return value (summary block fields, advisory detail, links, alternative versions). Also covers failure modes and ecosystem limitations, making it complete 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?

Input schema has 100% coverage with descriptions for package and version. Description does not add extra meaning beyond what schema provides, but the default behavior for version is mentioned. 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 performs a composite check for npm packages, combining data from deps.dev and bundlephobia. It specifies the verb (composite check) and resource (npm package), and distinguishes from siblings like entity_profile or generate_llms_txt.

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 describes when to use ('is X safe / popular / small' or 'what does adding lodash cost me') and when not to use (non-npm packages) with alternative suggestion. Also notes potential delay and graceful degradation.

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 read-only, idempotent, non-destructive behavior. The description adds significant detail: uses BGE-base-en embeddings with cosine similarity over 500-char overlapping windows, a 200K char cap with truncation and flagging, and that passages include character offsets for verification. 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, well-structured paragraph that front-loads the core purpose. Every sentence contributes useful information: use case, technical details, pairing suggestion, and limitations. 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?

Despite lacking an output schema, the description fully explains what is returned (top-N passages with character offsets and similarity scores). It covers the tool's mechanism, limitations (200K char cap, truncation), and how it integrates with other tools. For a 3-param tool, this is exceptionally 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 100%, so baseline is 3. The description adds value by providing concrete examples for the 'query' parameter (e.g., 'supply-chain risk', 'fiscal year 2024 revenue') and clarifying the default and range for 'limit'. While it does not add much to 'text' beyond schema, the examples elevate it above baseline.

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 performs 'semantic search INSIDE a fetched record' with specific examples (SEC 10-K, article, long tool result). It distinguishes from siblings by explaining the use case of retrieving relevant passages instead of the whole document, which is unique among 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?

The description explicitly states when to use: 'Use when the record is too big to cram into the prompt.' It also provides an alternative and pairing with 'ask_pipeworx_grounded', explaining how to combine tools for grounded generation.

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, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: required account type, type-specific parameter schemas, delivery channels with constraints (e.g., SMS cap, phone verification). However, it does not explicitly confirm idempotency behavior (whether duplicate subscriptions are allowed), which is a minor gap.

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 returns value. It is structured into sections for types and delivery, but is slightly verbose (e.g., listing all type examples inline). Still, every sentence provides value and avoids 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 (3 parameters, nested objects, no output schema), the description covers required authentication, all supported subscription types with parameter details, delivery channels with constraints, and the return value (subscription id). This is sufficient 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?

With 100% schema coverage, the description still adds significant meaning beyond the schema: detailed examples for each type (e.g., 'items:["5.02"] = officer change'), warnings for patent_grant approximate matching, and delivery channel details with verification requirements and caps.

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 'Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id.' This is a specific verb+resource combination. It effectively distinguishes from siblings like list_subscriptions (listing) and unsubscribe (removing).

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: requires a Pipeworx OAuth account, lists supported types with example parameters, and notes delivery constraints. However, it does not explicitly mention when NOT to use this tool or name alternative tools for one-off queries, though sibling tools provide implicit 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 adds critical behavioral context beyond annotations: ownership enforcement, soft delete (deactivation), and availability of historical events via recent_alerts. 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, front-loaded with action and id, no waste, efficiently conveys all necessary information.

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 one-param mutation tool with no output schema, the description is complete: explains behavior, ownership, and side effects. Sufficient for correct usage.

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%, and the description does not add additional semantic detail beyond what the schema already provides for the id 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 action 'Cancel a subscription by id' and differentiates from sibling tools like subscribe and list_subscriptions by specifying id-based cancellation.

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 context about ownership enforcement and deactivation behavior, but does not explicitly state when not to use or list alternatives. The context is clear enough for typical use.

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, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds useful behavioral context: data source (SEC EDGAR + XBRL), return format (verdict, structured form, citation, percent delta), and that it replaces 4-6 sequential calls. 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?

Description is front-loaded with usage examples and is structured logically. Every sentence adds value, though it could be slightly more concise. Still efficient for the amount of information provided.

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 simplicity (single parameter, clear annotations), the description covers purpose, scope, return values, and usage context comprehensively. No output schema exists, but the description explains return fields adequately. Complements annotations well.

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 (claim) with schema description coverage at 100%. The schema already provides examples. The description repeats some of that information but does not add significant new semantics 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 the tool performs natural-language claim verification, provides example query patterns ('Is it true that...', 'fact check'), and specifies it uses SEC EDGAR + XBRL for company-financial claims. It distinguishes itself by noting it replaces multiple sequential calls, differentiating it from 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?

Explicitly states when to use ('whenever the agent needs to check whether something a user said is factually correct') and defines scope (company-financial claims for public US companies). Lacks explicit when-not-to-use guidance but 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.