Data Nantes

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds critical behavioral context: Anthropic calls require user's own API key and direct payment, and the return structure includes per-model fields plus a combined view.

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

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

Three sentences front-loaded with purpose, then model details and use cases. No redundant information; each 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 details return structure (per-model {score, confidence, signals, raw_response} + combined view). It covers all parameters and provides clear use cases, making it complete for a probe-and-score 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 good descriptions. The description adds meaning by explaining the default model, how to enable Anthropic, and providing an example for 'entity'. It goes beyond the schema by contextualizing parameter usage.

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 probes LLMs for knowledge about a business/brand/product/topic and scores visibility (0-100) per model. It distinguishes from sibling tools like 'scan_competitor_ai_presence' by focusing on scoring per model with a combined view.

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 cases are given (AI-marketing audits, pre-launch brand checks, competitive monitoring). It also explains model selection (default workers-ai, optional Anthropic with _apiKey). No 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 declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, and the description adds useful behavioral context: it routes to a large tool ecosystem, fills arguments automatically, and returns citation URIs. There is no contradiction between the description and 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 comprehensive and front-loaded with the key preference instruction, followed by examples and sibling routing guidance. It has minor redundancy, such as repeating 'even if web search could also answer it', which keeps it from a perfect conciseness score.

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

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

Since there is no output schema, the description compensates by explaining that the return value is a structured answer with citation URIs. It also provides enough routing guidance and examples for an agent to select and invoke the tool correctly, though it does not cover failure modes or limitations.

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 all six parameters are documented as aliases for the natural-language question. The description adds example queries and trigger phrases but no additional parameter-level semantics, so the 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?

The description clearly states that this tool routes questions to one of 5,767 tools across 1,506 verified sources and returns structured answers with stable pipeworx:// citation URIs. It distinguishes itself from siblings by explicitly naming ask_pipeworx_grounded and deep_research as escalation alternatives, so an agent can tell them apart.

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 to prefer this tool over web search for factual/structured data questions, provides trigger phrases like 'what is', 'look up', and 'get the latest', and gives concrete examples. It also states when to use alternatives: ask_pipeworx_grounded for hallucination-resistant single answers and deep_research for broad/multi-part questions.

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 readOnly/idempotent annotations, the description discloses that candidate routing changes may be active live, that none are active now so behavior matches ask_pipeworx exactly, and that this is a fully functional router with no fallback. This gives the agent a strong sense of what can change and why.

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 longer than average but each sentence adds meaningful context: beta status, exact equivalence, active-candidate status, usage direction, and comparison purpose. It is well-structured and front-loaded with the most important identity 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?

The description covers the tool's identity, current behavior, experimental nature, and how to use it relative to ask_pipeworx. It relies on the reader knowing ask_pipeworx for full output-shape details, but it explicitly says the response shape is identical, which is sufficient given the schema 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?

The input schema already covers all parameters with 100% description coverage, including aliases for question. The description adds little parameter-specific meaning beyond noting that arguments are identical to ask_pipeworx, which is useful but not necessary given the schema detail.

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 this is a beta version of ask_pipeworx, an identical universal router with the same tools, arguments, and response shape. It also distinguishes the tool from the stable ask_pipeworx by explaining candidate routing improvements and the current no-active-candidate state.

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 to use it exactly like ask_pipeworx when the newest routing is desired, which gives a clear selection condition. It names the stable router as the comparison baseline but does not explicitly state when to avoid this tool in favor of ask_pipeworx.

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 fully discloses success and refusal behaviors, including the exact return shape with evidence, confidence, and refusal_reason values. It goes well beyond the readOnlyHint/openWorldHint annotations by explaining how it handles unsupported, truncated, or unmatched data, and notes the extra LLM call cost.

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 dense but well structured, front-loading the core purpose and then covering behavior, return shape, usage guidance, and cost comparison. A few phrases repeat the groundedness idea, but every sentence contributes useful decision-making 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?

Even though there is no output schema, the description enumerates success and refusal return objects, including specific refusal_reason values, which fully substitutes for structured output documentation. Given only one required parameter and clear routing guidance, nothing essential is missing for an agent to invoke this tool correctly.

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

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

Schema description coverage is 100% and all six parameters are documented as aliases for 'question', so the schema already carries the parameter semantics. The description adds no new parameter-level detail beyond implying a natural-language question, which is acceptable given the baseline for full schema coverage.

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

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

The description names a specific mode: a hallucination-resistant, grounded answer tool that extracts answers only from tool results. It clearly distinguishes itself from ask_pipeworx and ask_pipeworx_beta by emphasizing evidence-grounded extraction rather than general lookup.

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 when to use it: whenever an answer will be quoted, cited, or acted on and facts must not be invented, with examples like financial and legal claims. It also gives a cost-based exclusion: prefer ask_pipeworx for casual lookups because this tool costs an extra LLM call.

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 significant behavioral context beyond annotations: it explains that low-confidence resolutions short-circuit with status:'low_confidence_match', closed markets return 'market_closed_or_inactive', and wide spreads carry 'illiquid_wide_spread'. It details resolver contract and parent event extraction. No contradiction with annotations (readOnlyHint, openWorldHint, 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?

The description is lengthy but well-structured, with clear sections for resolver contract, parent extractor, news fields, safety, etc. Every sentence adds value, though some details could be condensed. The length is justified by the tool's complexity.

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 all aspects: input types, output shapes (market, analysis, evidence), resolver contract, parent event extraction, news fields, safety mechanisms, resolution rule risk, and parameter explanations. No output schema exists, so the description fully compensates by describing return values in detail.

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 substantial meaning: it explains that market can be a slug, URL, or question text; depth options (quick vs thorough); include_raw (false recommended for summary, true for raw payloads). Examples further clarify usage.

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's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It details inputs (slug, URL, question text) and outputs (evidence packet + market-vs-model comparison). This distinguishes it from siblings like polymarket_arbitrage and polymarket_edges, which focus on different aspects.

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 usage scenarios: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It also advises on when to inspect market_match_confidence before trusting analysis, and warns about resolution rule risk. No explicit when-not-to-use, but the scenarios imply 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=true and destructiveHint=false, so the safety profile is clear. The description adds rich behavioral details: data sources (SEC EDGAR/XBRL, FAERS), handling of fiscal years, sorting by primary metric, and output format with citation URIs.

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 lengthy but every sentence adds value. It is front-loaded with trigger phrases and core function. Could be slightly tighter, but overall efficient.

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

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

Given the tool's complexity (handling two entity types with different data sources) and lack of output schema, the description covers the main return values and data sources. The mention of 'paired data' is a bit vague, but it suffices for basic understanding.

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%, but each parameter description is brief. The main description adds useful context: what 'type' triggers for companies vs drugs, and examples for 'values' (tickers, drug names). This enhances meaning beyond the schema, earning 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 compares 2-5 companies or drugs side-by-side, using verbs like 'compare', 'rank', and 'head to head'. It distinguishes from siblings by explicitly recommending preference over sequential single-pack 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?

The description provides explicit trigger phrases (e.g., 'Compare X and Y', 'X vs Y', 'which is bigger') and explains when to use (for comparisons) and when not to (prefer over sequential lookups). It also gives examples of queries.

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, and non-destructive behavior. The description adds value by specifying what metadata is returned (fields/schema, themes, record count), which is useful since there is no output schema.

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 sentence that front-loads the core purpose. Every word contributes value without redundancy.

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

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

The description succinctly covers what the tool returns (fields/schema, themes, record count), which is sufficient for a metadata tool with no output schema. It could mention that it does not return actual data, but the mention of 'metadata' implies this.

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 only parameter dataset_id is described in the schema as 'from search_datasets,' and the tool description reinforces that context. However, the description does not add new meaning beyond what the schema already provides, so it's adequate but not exceptional.

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 gets metadata for a Nantes Métropole Open Data dataset, specifying fields/schema, themes, and record count. It distinguishes from sibling tools like search_datasets and query by indicating this is a preliminary step to learn column names before querying.

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 'call before query to learn the column names,' providing clear guidance on when to use this tool. While it does not list alternatives, the context makes the usage intent obvious.

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 readOnly/openWorld/idempotent/non-destructive, and the description adds substantial context beyond that: account/paid-tier constraints, explicit gaps[] and 'never invented,' contradiction[] behavior for standard/thorough, hop and citation_uri semantics, semantic excerpting, and latency expectations. No annotation contradiction exists.

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 account prerequisite and fallback tool, and every sentence carries operational value. It loses a point for being an unusually dense run-on paragraph; grouping the auth, depth/hop, and output-packet details into clearer sections would make the critical routing conditions easier to parse.

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

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

There is no output schema, so the description carries the full burden of explaining return values. It comprehensively covers output shape (evidence/confidence/source/fetched_at/citation), gaps[], contradictions[], hop/citation_uri, depth behavior, auth boundaries, and latency. For a tool of this complexity, nothing material 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 description coverage is 100%, so the baseline is 3. The description adds some timing and example context, but the key depth semantics (quick=3, standard=3 with gap recovery and contradictions, thorough=6 paid) are already fully documented in the input schema's depth property. There is not enough added parameter meaning to exceed the 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?

Description names a specific operation ('grounded multi-source research'), concrete resource ('Pipeworx's 1506 STRUCTURED data sources'), and mechanism (decomposes, routes in parallel, returns findings packet). It also explicitly contrasts with 'open-web search' and distinguishes from ask_pipeworx, so an agent can tell what this tool is and is not.

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 ('best for broad/multi-part questions over structured data'), when-not-to-use ('For a single lookup use ask_pipeworx instead'), and an auth-based fallback ('If you are not signed in, use ask_pipeworx instead — it works on every tier'). This fully routes an agent to the right sibling.

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, destructiveHint=false, idempotentHint=true. Description adds valuable behavioral details: returns top-N tools with full schemas ready to call, no second lookup needed. It also lists specific data domains, providing context on what the tool can search.

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 clear and front-loaded with purpose. However, it includes a long list of domains which, while useful, could be slightly more concise. Still well-structured and every sentence adds value.

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

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

Given no output schema, the description adequately explains what is returned: top-N tools with names, descriptions, and full input schemas (with curated examples). It also specifies the default and max limits. No gaps for functional understanding.

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%. Description enhances parameter meaning: explains query accepts natural language, lists aliases (task, q, description, search), provides examples, and describes limit behavior. Adds that results are 'ready to call' without additional lookups.

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 'Find tools by describing the data or task.' The verb 'find' and resource 'tools' are explicit. The description distinguishes this tool from siblings (e.g., 'query', 'search_datasets') by specifying it is for discovering tools, not data. Includes a list of domains to further clarify scope.

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: 'Use when you need to browse, search, look up, or discover what tools exist for...' and 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This provides clear context and 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?

The description goes far beyond the readOnly/openWorld/idempotent annotations: it discloses source fan-out, sources_used/sources_failed behavior, that empty sections mean real no-data results, patents soft-fail status, and the private-company resolved:false path. These are non-obvious behaviors an agent must know to interpret results correctly.

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 dense and fairly long, but it is front-loaded with usage examples and the key preference directive. The source list and edge-case explanations earn their place, though the final type-interchangeability sentence is somewhat redundant with the schema.

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

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

With no output schema present, the description compensates thoroughly: it enumerates return fields (CIK, recent_filings with URIs, fundamentals, source lists), explains failure representations, and covers edge cases such as private companies. An agent has enough context to invoke and interpret the tool correctly.

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

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

The input schema already fully describes both parameters, including accepted examples, company-name resolution via SEC EDGAR, and the fact that type values are interchangeable. The description mostly restates this schema information rather than adding new parameter-level semantics.

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

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

The description clearly defines the operation: build a full cross-source profile of a US public company in one call. It provides multiple natural-language entry examples and explicitly frames the tool as the preferred holistic alternative to chaining individual 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?

It explicitly instructs the agent to prefer this tool over chaining SEC/XBRL/news lookups when the user wants a holistic view. It also specifies accepted inputs (ticker, CIK, company name), the company scope, and what happens for private companies (resolved:false), which is effective 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 indicate destructive and idempotent behavior. The description adds context about clearing sensitive data, but does not mention what happens if the key does not exist or confirm persistence of deletion. Still, it aligns with annotations and adds moderate value.

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

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

Two sentences: first states purpose, second provides usage and pairing advice. No extraneous information, front-loaded structure.

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 (1 param, no output schema), the description covers purpose, when to use, and related tools. Minor gaps like return value or error handling, but overall complete for a simple deletion 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 'key' whose description is 'Memory key to delete.' The description does not add new semantics beyond the schema, so 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 'Delete a previously stored memory by key,' specifying a concrete action on a defined resource, and it distinguishes itself from siblings 'remember' and 'recall' by implying deletion versus storage or retrieval.

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 provides when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data.' Also advises pairing with related tools, giving clear usage 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 indicate read-only, idempotent, and non-destructive behavior. The description adds valuable detail about the process (fetching, extracting, emitting markdown) and the output format (single text blob for site-root/llms.txt), going beyond the 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?

The description is two sentences with no wasted words. It front-loads the main action and purpose, then provides context and uses cases. Excellent balance of detail and brevity.

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 the output format and process. The tool is simple (2 params, no nesting), and the description covers all necessary information for correct invocation, 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 description coverage is 100%, so the parameters are already well-documented. The description does not add new semantic information beyond restating defaults (max_links default 25, max 50). 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's purpose with a specific verb and resource ('Generate a production-ready llms.txt file for any URL'), and lists concrete use cases that distinguish it from sibling tools like 'scan_competitor_ai_presence' or 'ai_visibility_check'.

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 (e.g., indexing client sites, drafting for own projects, auditing competitors), which helps the agent decide when to use it. However, it doesn't mention when NOT to use or list alternative tools, preventing a perfect score.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false. The description adds the field list but no additional behavioral traits 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?

The description is two sentences, front-loading the core purpose and immediately providing usage guidance with no redundant 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?

Although no output schema exists, the description lists return fields. The tool is simple and the description covers its essential aspects, though pagination details are 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% and the description adds no extra meaning to the include_inactive parameter 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 'List the caller's active subscriptions' with a specific verb and resource, clearly distinguishing from siblings like subscribe 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?

The description provides explicit usage context: 'Use this to review what you're monitoring before adding more or to find an id to cancel,' though it does not specify 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 are all false and provide little safety context, so the description carries the burden. It discloses side effects (filing feedback, returning claim_token), rate limits (5/day), cost (free), and downstream impact (digests read daily). This goes well 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 long but every sentence carries useful information: purpose, use cases, exclusions, token flow, rate limits, and cost. It is front-loaded with purpose and logically organized, though slightly dense.

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

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

With no output schema, the description explains the key return value (claim_token) and how to use it later. It covers rate limits and scope, but does not fully describe the complete response format or error cases. Still, it is sufficient for a feedback submission 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% and the schema already describes each parameter thoroughly. The description adds a concrete usage example for claim_token and clarifies how to reference Pipeworx tools, which adds value 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 opens with a specific verb and resource: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It clearly distinguishes from siblings like ask_pipeworx by focusing on feedback rather than queries, and explicitly excludes tools from other MCP servers.

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 categories (bug, feature/data_gap, praise) and explicit when-not-to-use (tools from other MCP servers). Also explains the claim_token workflow for checking status, which is a key usage pattern.

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, not destructive), the description discloses data source (CF analytics-engine), privacy implications (no PII), and caching behavior (5min-1h). This adds value without contradicting 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: one sentence for purpose, then bullet-style use cases, then technical details. Every sentence serves a purpose 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?

For a simple read-only tool with one optional parameter and no output schema, the description fully covers purpose, output shape, caching, and privacy. 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 coverage is 100% (only parameter 'window' with enum). Description adds meaning: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' This helps the agent choose between options.

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 specifies exactly what the tool does: 'Returns the top tools, top packs, and total call volume over a recent window'. It uses a specific verb+resource and distinguishes from siblings by focusing on trending analytics, which no other sibling tool does.

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

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

The description lists three explicit use cases: discovering hot data sources, confirming canonical tool, and aligning use case with agent needs. While it doesn't state when not to use or name alternatives, the guidance is clear and practical.

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 beyond the annotations (readOnlyHint, idempotentHint, openWorldHint, non-destructive). It explains semantic anchor (Jaccard similarity), partition filter, fill check with realizable edge, and conditions for not trading. 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 detailed and front-loaded with the core purpose, but it is somewhat verbose, containing many technical specifics. Every sentence adds value, but a slightly more condensed version could improve conciseness without losing clarity.

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 comprehensively covers the response structure, including fields like opportunities[], partition_check, and fill check details. All modes and parameters are fully explained, making the tool's behavior and output 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 basic descriptions, but the description adds substantial context: for event it explains walking child markets and partition checks; for topic it explains cross-event scanning and similarity checks. This greatly enriches parameter 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's purpose: finding arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes three modes (no args, event, topic) with specific use cases, making it highly specific and differentiated from siblings.

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

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

The description provides explicit guidance on when to use each mode: 'Call with NO args for a trending_scan', 'pass event for the strongest per-event partition_check', 'topic for a themed cross-event scan'. It also references a sibling tool for custom sizing. However, it does not explicitly state when not to use this tool versus all sibling tools like polymarket_edges or polymarket_edge_tracker.

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?

All annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) are consistent and the description adds significant context beyond them: detailed breakdown of model families and their calculations, edge_pp_net (net of slippage), kelly fractions with caps, tradeable-edge knobs, diagnostics for empty segments, and caching behavior. The description discloses the tool's behavior thoroughly.

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 dense but well-structured: it opens with a clear headline purpose, then breaks into segments and fields. Each segment is explained with sufficient context. However, it is long and could benefit from bullet points or clearer separation; currently it is one block of text. Still, it earns its length for the complexity.

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 9 parameters, no output schema, and annotations, the description is remarkably complete. It details the return structure (by_segment, fed_candidates, _diagnostics), explains edge fields and their meanings, describes the tradeable-edge filters, and mentions caching. There are no apparent gaps; an agent can fully understand the tool's behavior from this description.

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 schema comments are already comprehensive (e.g., min_kelly explains half-Kelly fraction and default). The tool description adds no additional parameter-level detail beyond grouping and high-level context. As per guidelines, with high coverage, a 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's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It specifies the use case ('what should I bet on today') and directly addresses the agent's need without ambiguity. Distinguishes from sibling tools by its focus on Pipeworx data and opportunity 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 a usage context ('for what should I bet on today') and explains how to use knobs (e.g., min_liquidity, max_spread_pp). However, it does not explicitly compare to alternatives like polymarket_arbitrage or polymarket_edge_tracker, nor does it state when not to use this tool. The guidance is useful but incomplete for an agent deciding among siblings.

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

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

The description adds behavioral context beyond annotations, including snapshot TTL, data gaps, and decay computation from daily closes. No contradictions with annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false).

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 purpose and contains valuable details, but is somewhat lengthy. Every sentence contributes, though some restructuring could improve 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 simple parameters and no output schema, the description fully details the response structure (tracked, expired, snapshot_dates) and limitations (TTL, data gaps), 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 parameter descriptions. The description adds minor clarifications (e.g., clamp 2-30 vs max 30, default 14) but does not significantly enhance understanding 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 it provides edge persistence and decay telemetry, answering 'how long has this edge existed and is it shrinking?' It distinguishes itself from siblings like polymarket_edges by focusing on historical persistence rather than current edges.

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

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

The description implies usage through the example contrasting fresh vs. 3-week-old edges, but does not explicitly state when to avoid this tool or mention alternatives. Given the context of sibling tools, the usage is clear but lacks explicit exclusions.

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

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

While annotations already indicate readOnly, idempotent, and non-destructive behavior, the description adds substantial context: it walks the order book ladder, returns a verdict (clean|degraded|cannot_fill), and warns about thin books and forced directional risk. This fully informs the agent of behavioral traits 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 dense and front-loaded with the core purpose, but it packs a lot of information into a single paragraph. While effective, it could be slightly more structured (e.g., bullet lists for return values) to improve scannability. Still, 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?

Given the tool's complexity (two modes, multiple return fields, no output schema), the description provides a remarkably comprehensive overview. It enumerates all key return fields for both modes (e.g., top_of_book, vwap_fill_price, capture_ratio, forced_directional_risk) and explains the dominant failure mode, leaving no critical 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 significant semantics: it clarifies that side defaults to 'auto' for basket mode, size_usd is clamped to 10–1,000,000 (not in schema), and it explains the REQUIRES constraint (market or event). This goes well beyond the 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: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes between single-market and basket modes and explicitly ties its usage to sibling tools like polymarket_arbitrage and polymarket_edges, making its role in the tool ecosystem unmistakable.

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 guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also warns against partial basket fills converting an arb into an unhedged directional position, giving clear when-not-to-use 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?

The description goes far beyond the readOnlyHint/idempotentHint annotations, disclosing that returned pairs may be unverified, that compatibility_codes can be non-empty even when pairs are returned, that spreads are gross not net of Kalshi fees, and that unknown metric types are never paired. It also explains temporal_alignment null semantics and skipped-comparison counters. This is rich, honest behavioral disclosure with 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 long but every sentence earns its place, especially because there is no output schema to carry return-value documentation. It is front-loaded with the core purpose and then uses clear labels like TWO MODES, RESPONSE, and SAFETY FIELDS to organize dense information. Despite its length, it remains scannable and free of filler.

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

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

With no output schema and no nested-object definitions, the description carries the full burden of explaining response semantics, and it does so thoroughly: leg prices, top_spreads_pp, compatibility codes, per-entry flags, skipped_unclassified, temporal_alignment, fees_note, and skipped counters. An agent has enough information to call the tool, interpret results, and understand limitations. 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?

The schema already covers all three parameters at 100% with descriptions, so the baseline is 3. The description adds meaningful mode-level context: topic-only versus explicit ticker+slug, the override relationship between them, and the fact that identical matching logic applies in both modes. This enriches parameter understanding beyond individual schema entries.

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 function: computing cross-venue spreads between Kalshi and Polymarket for the same resolving question. It specifies the resource and the analytic intent, and the two-mode design is explained. It does not explicitly name or contrast sibling tools like polymarket_arbitrage, so it stops short of the top score.

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 strong usage context by explaining two modes: pre-mapped topic shortcuts versus explicit ticker/slug pairings, and it notes that both modes run the same matcher. It also warns that pre-mapped topics often return compatibility warnings, which helps an agent decide whether the shortcut is trustworthy. However, it does not explicitly say when to prefer this tool over sibling alternatives, so no exclusion guidance is provided.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds context about using ODSQL and the specific dataset, confirming the read-only nature. 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 sentence with no wasted words. It front-loads the core action and then succinctly lists the operations in parentheses. Highly 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?

The description covers the key operations but omits information about return format or any limitations. Given there is no output schema, the agent might need more context about what the response contains (e.g., structure of records). Adequate but not fully complete.

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

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

Schema coverage is 100%, so baseline is 3. The description enhances understanding by grouping parameters into categories (filter, aggregate, sort, paginate), which adds semantic structure beyond the schema's individual 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 queries records from a specific dataset (Nantes Métropole Open Data) using ODSQL, and lists filtering, aggregation, sorting, and pagination. This verb+resource combination distinguishes it from siblings like search_datasets and dataset_info.

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

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

Usage context is implied by the purpose, but there is no explicit when-to-use, when-not-to-use, or mention of alternatives. The description does not guide the agent on when to prefer this over similar tools like search_within.

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, destructiveHint. The description adds scope details (IP, key hash, account ID) and pairing behavior, providing useful 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, front-loaded with purpose, no superfluous words. Every sentence contributes essential 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 retrieval tool with one optional parameter and comprehensive annotations, the description fully covers scope, pairing, and usage. No output schema needed as return values are implied.

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 'key' has schema description 'Memory key to retrieve (omit to list all keys)'. The description reinforces the omitting behavior and adds usage context, adding value beyond the schema's baseline 3 for high coverage.

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

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

The description states 'Retrieve a value previously saved via remember, or list all saved keys', clearly indicating the verb (retrieve/list) and resource (saved memory). It 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?

The description explains when to use (look up context stored earlier, avoid re-deriving) and mentions pairing with remember/forget. It does not explicitly state when not to use, but provides 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?

The description states that setting mark_read:true flags events as read, which implies a state change. However, annotations include readOnlyHint:true, indicating no writes. This contradiction undermines transparency, resulting in a score of 1.

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

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

The description is concise (4 sentences) with the main verb and resource front-loaded. Every sentence adds detail without redundancies, making it efficient for the agent to parse.

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 structure (source, citation_uri, payload), covers filter behavior, and mentions side effects of mark_read. It adequately covers all necessary information for a tool with five optional 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 coverage is 100% and parameters have descriptions. The description adds value by providing examples (e.g., 'sec_8k' filter, ISO timestamp) and clarifying the effect of mark_read, going beyond the schema's 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 the tool pulls fired events from the subscription feed and specifies the returned data (source, citation_uri, payload). It distinguishes itself from siblings by focusing on alerts retrieval, 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 context on filtering by type and since, mentions polling suitability, and notes an alternative URL for scripts/dashboards. It does not explicitly exclude scenarios but offers clear usage guidance for the intended purpose.

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

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

Beyond annotations (readOnlyHint, idempotentHint), description details parallel calls, news fallback logic (GDELT→GNews), USPTO soft-fail due to API sunset, and output structure with grouped changes and citation URIs.

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 packed with examples and details, but front-loaded with query patterns. Slightly verbose but every sentence serves a purpose. Could be tightened slightly.

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 (changes grouped by source, total_changes, citation URIs) and covers edge cases like fallback behavior and API sunset. Complete for the tool's complexity.

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?

Despite 100% schema coverage, description adds practical usage guidance: explains relative date formats, suggests '30d' for monitoring, clarifies value accepts ticker or CIK, and notes type is limited to 'company'.

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 provides a change feed for a company, listing recent updates across SEC, news, and patents. It distinguishes from sibling entity_profile which serves 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?

Explicitly lists query examples and when to use (e.g., 'What's new with X'), and directs to entity_profile for static profiles. Provides clear context for choosing between 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?

Beyond annotations, describes scoping by identifier, persistence difference between authenticated (permanent) and anonymous (24 hours). 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?

5 sentences, front-loaded purpose, every sentence provides value. 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?

Fully explains storage behavior, scoping, and expiration for a simple write tool with no output schema.

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

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

100% schema coverage provides full parameter descriptions. Description adds naming convention examples but doesn't significantly augment semantics 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?

Description states 'Save data the agent will need to reuse later' – a specific verb+resource. It distinguishes from siblings recall and forget, making the purpose 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 says 'Use when you discover something worth carrying forward' and gives examples. Mentions complementary tools (recall, forget). Lacks explicit when-not-to-use, but 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?

Despite readOnlyHint and idempotentHint annotations, the description adds substantial behavioral context: it cascades through multiple lookup endpoints, replaces 2–3 manual lookups, degrades gracefully when GLEIF/OpenFIGI are unavailable, returns `figi_candidates` on ambiguity, and explicitly reports unresolved identifiers. This goes far beyond what annotations alone convey.

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 long and dense, with many nested parentheticals, but it is front-loaded with purpose and usage guidance before diving into per-type details. Every major clause earns its place; the density reduces readability slightly, but there is no filler or tautology.

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

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

For a complex multi-source lookup with no output schema, the description covers input semantics, supported types, ambiguity behavior, unresolved identifier reporting, source labeling, ISIN-to-LEI mapping, and graceful degradation. An agent has enough context to select and invoke the tool correctly and to interpret common edge cases.

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 high-value guidance: the `value` parameter must be the entity name only, bond issuer names must be passed exactly as printed, and trailing security-class words should be omitted because they match nothing. This kind of error-preventing detail is exactly what the description should add 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 states a specific verb and resource: 'resolve a user-spoken NAME to the canonical/official identifiers other tools require as input.' It then enumerates concrete example queries and the supported entity types ('company', 'drug'), making it unmistakable what this tool does and how it differs from tools that consume identifiers rather than produce them.

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

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

The description gives an explicit usage rule: 'Use FIRST whenever you have a name but need an ID.' This clearly identifies the triggering condition. It does not name specific sibling tools to avoid, but the condition 'other tools require as input' implies the tool is a lookup prerequisite rather than a profiling or comparison tool.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, indicating a safe, non-destructive, and potentially non-deterministic operation. The description adds behavioral details: it outputs a ranked list with score, confidence, and signal density per entity, and internally uses 'ai_visibility_check'. 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 two sentences: first states the core action (compare and rank), second gives a practical use case and output summary. 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?

With no output schema, the description explains the return format (ranked list with score, confidence, signal density). Parameter descriptions are fully covered in schema. The description differentiates from siblings, mentions internal tool usage, and provides a realistic usage example. All aspects are addressed.

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% with good parameter descriptions. The tool description adds value by explaining that the first entry in 'entities' is treated as the 'subject' for narrative purposes, and that 'context' is shared across probes. This nuance goes beyond the schema, justifying above 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 compares AI visibility across multiple entities, ranks them by score, and surfaces which is most/least recognized. It distinguishes itself from siblings like 'ai_visibility_check' (single entity) and 'compare_entities' (generic comparison) with a specific verb 'scan' and concrete use case example.

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 a clear use case ('competitive AI-marketing audits') and an example question. It implicitly suggests using 'ai_visibility_check' for single entity checks by stating it probes each entity with that tool, but does not explicitly list alternatives or state when not to use. This is slightly lacking for a top score.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds value by detailing partial failure modes (bundlephobia first measurement can take 5-30s, sources_failed listed), which supplements the 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?

Description is relatively long but front-loaded with the main purpose. Each sentence adds value (behavior, limitations, return content). Could be slightly more concise, but 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?

Without an output schema, the description thoroughly lists return fields (summary block, per-advisory detail, links, alternative versions). It also explains partial failure behavior and ecosystem limitations, making it complete for the 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 has 100% description coverage for both parameters. Description adds practical context: scoped packages accepted (e.g., @types/node), version defaults to latest. This goes beyond schema, providing useful usage guidance.

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

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

The description clearly states it is a composite check for npm packages, combining deps.dev and bundlephobia. It uses specific verbs ('scan', 'check') and identifies the resource (npm package). Sibling tools include various unrelated tools; this tool's purpose is 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?

Explicitly advises when to use: 'whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also notes scope limitations (NPM ecosystem only in v1) and handles partial failures gracefully, providing guidance on expected behavior.

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. Description adds return value details (dataset_ids, titles, themes, record counts) but no additional behavioral context (e.g., data source freshness, permissions).

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 efficient sentences with no wasted words. Front-loaded with action and scope. Compact yet informative.

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 purpose, return type, and relationship to sibling tools. Lacks discussion of pagination behavior or error cases, but schema covers offset/limit limits. Sufficient for a simple search tool with no output schema.

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

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

Schema description coverage is 100% for all 3 parameters. The description does not add new parameter insights beyond the schema (e.g., date filtering, format requirements). 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?

Clearly states verb 'Search', resource 'Nantes Métropole Open Data datasets', and what is returned (dataset_ids, titles, themes, record counts). It also distinguishes from sibling tools by mentioning passing dataset_ids to query/dataset_info.

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?

Implies when to use: for searching datasets by keyword. References related tools (dataset_info, query) for further steps. Does not explicitly state 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?

Adds significant detail beyond annotations: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flagging. All annotations (readOnly, idempotent, openWorld, non-destructive) are consistent and reinforced.

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 front-loaded purpose, clear examples, and technical details. Every sentence serves a purpose without redundancy. Concise while covering all essential aspects.

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, description fully explains return values (passages with character offsets and similarity scores). It also covers edge cases (200K char cap, truncation flagging) and hints at embedding details. Complete for the tool's complexity.

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 value with concrete examples (SEC 10-K, natural-language query examples). For text and query parameters, it provides usage context beyond schema descriptions. Limit parameter is implied ('top-N') but not explicitly restated.

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' with specific examples (SEC 10-K, article, long tool result). It clearly distinguishes the tool's scope as searching within previously fetched content, differentiating it from tools that fetch or search externally.

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 clear when-to-use guidance: 'Use when the record is too big to cram into the prompt... saves context, returns only the passages that matter.' Also mentions pairing with ask_pipeworx_grounded. Lacks explicit when-not-to-use or alternatives, but context is strong.

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

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

The description contradicts the idempotentHint annotation: it states 'Returns the new subscription id,' implying non-idempotent creation, while idempotentHint=true suggests idempotency. This inconsistency warrants a score of 1. The description otherwise provides rich behavioral context, but the contradiction lowers the score.

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

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

The description is well-structured with clear sections and examples, but it is lengthy. It efficiently conveys necessary information without irrelevant details, earning a score of 4.

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, enums, delivery channels), the description is remarkably complete. It covers all relevant aspects: prerequisites, type-specific params, delivery options with constraints, and return value. No output schema exists, but the description adequately explains the return value.

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 a baseline of 3. The description adds substantial meaning by explaining each enum value for type with concrete examples and specific parameter structures, and details delivery options with constraints, significantly enhancing understanding 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's purpose: 'Create a proactive monitoring subscription to a live-data event stream.' It uses a specific verb and resource, and distinguishes it from siblings like list_subscriptions and recent_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?

The description mentions prerequisites (Pipeworx OAuth account) and provides examples for each subscription type with parameters, implying when to use each. However, it lacks explicit 'when not to use' or direct comparisons to sibling tools beyond a brief mention of the feed 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 indicate read-only, idempotent, open-world, non-destructive. The description adds behavioral context: returns live examples from catalog, uses no arguments for full spread, supports topic filtering. 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 somewhat long but every sentence adds value. It front-loads common user queries and structures content logically. Minor verbosity 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 fully explains the return structure (category-bucketed examples with tool shapes). Covers all scenarios and is complete for an onboarding 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% and the description goes beyond by explaining the effect of omitting the topic parameter and listing specific allowed values. Provides practical usage 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 tool returns category-bucketed example questions with tool+argument shapes, serving as the onboarding entry point. It distinguishes from siblings like ask_pipeworx by focusing on exploration.

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 recommends using this tool first when unsure of Pipeworx capabilities, and mentions meta-tools. Provides guidance on when to call without arguments vs with a specific topic.

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 deactivation (not deletion) and that historical events remain available via recent_alerts. Annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true) already indicate mutation is safe and idempotent; description adds valuable 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?

Two efficient sentences: purpose first, then ownership and behavioral detail. No filler, 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 covers purpose, ownership, and side effects completely, referencing relevant sibling tool (recent_alerts).

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 parameter 'id' is fully described in schema (100% coverage). Description adds no additional meaning beyond stating 'by id' and referencing subscribe, which is already in 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?

Clear verb 'Cancel' and resource 'subscription by id'. Distinguishes from sibling tools like 'subscribe' and 'list_subscriptions' by specifying ownership and deactivation behavior.

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 ownership enforcement, guiding when to use: only for own subscriptions. No when-not-to-use or explicit alternatives mentioned, 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?

The description goes far beyond the readOnly/idempotent annotations by detailing behavioral traits: the two verification pipelines, the precise semantics of could_not_verify vs. unsupported (including that could_not_verify must not be treated as evidence and carries verification_error{stage,detail}), and the return contract of verdict, actual value with pipeworx:// citation, and reasoning. This adds rich context that annotations alone do not 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?

The description is a multi-sentence paragraph, but every sentence contributes value: usage trigger, routing explanation, output contract, error semantics, and performance advantage. It is front-loaded with example queries and could be slightly trimmed, but it is not verbose or padded, earning a solid 4.

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

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

With no output schema, the description compensates thoroughly by enumerating all verdict types, explaining error cases (could_not_verify vs. unsupported), describing return fields (verdict, actual value, citation, reasoning), and outlining the two routing branches. It covers both complexity and downstream interpretation, making it highly 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?

The input schema already has detailed descriptions for both parameters (tolerance_pct includes allowed range, override behavior, and default; claim includes examples). Schema description coverage is 100%, so the baseline is 3. The tool description adds no additional parameter semantics beyond the schema, so no higher score is warranted.

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 performs natural-language claim verification against authoritative sources, with specific example queries and a precise output (verdict, actual value with citation, reasoning). It distinguishes itself from generic search tools by focusing on fact-checking and highlighting that it replaces 4–6 sequential calls, 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?

It explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and explains the two routing paths (SEC EDGAR for company-financial claims, grounded pipeline for any other factual claim). However, it does not explicitly state when not to use the tool or name alternative tools for excluded scenarios, so it lacks explicit when-not or alternative guidance.

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