Pvgis

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds valuable behavioral context: it specifies the return structure (per-model {score, confidence, signals, raw_response} + combined view) and notes that Anthropic calls require the user's own API key with direct payment, which is not covered by 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 (two sentences), front-loaded with the main action, and every sentence adds essential information without redundancy.

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

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

Given the tool has 4 parameters, no output schema, and moderate complexity, the description adequately explains usage, return format, and different model options. It covers the key aspects needed for an agent to correctly invoke the 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?

All parameters have descriptions in the schema (100% coverage). The description adds extra meaning: it explains the default model, clarifies that _apiKey is passed through to Anthropic's API, and that context helps disambiguate entities, providing 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 clearly states the tool's purpose: to probe LLMs for visibility about a specific entity, scoring it 0-100. It uses a specific verb ('probe') and resource ('LLMs'), and distinguishes from siblings like 'compare_entities' or 'ask_pipeworx' by focusing on multi-model visibility scoring.

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 use-case guidance ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains when to use the default vs. Anthropic model. However, it does not explicitly mention when not to use this tool or provide direct comparisons to sibling tools.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds genuinely useful behavioral context beyond the annotations: it intermediates across thousands of sources, auto-fills arguments, and returns pipeworx:// citation URIs — signaling that the agent only needs to supply a natural-language question.

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 most decision-relevant directive ('PREFER OVER WEB SEARCH') and packs a dense list of domains, triggers, and examples with little waste. It is long, and the trailing guidance is slightly cramped/garbled, but every sentence earns its place.

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

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

For a complex routing tool with no output schema, the description covers what it does, when to use it, what not to use it for, examples, and citation behavior. Minor gaps remain around return format details and rate limits, but the required single parameter and safety profile are fully 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 coverage is 100% and the schema documents all six parameters as aliases with a clear description of the question field. The description adds value by stating that the tool 'fills arguments' itself, which tells the agent it does not need to guess about hidden parameters or argument formats.

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

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

States a specific verb-resource pairing: routes questions to 5,710 tools across 1,494 verified sources and returns structured answers with stable citation URIs. The domain list (SEC filings, FDA drugs, FRED/BLS, etc.) plus the explicit contrast with web search distinguishes it clearly from sibling tools like deep_research and ask_pipeworx_grounded.

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?

Opens with an explicit 'PREFER OVER WEB SEARCH' directive and gives concrete trigger phrases ('what is', 'look up', 'find', 'get the latest', 'how much', 'current') plus worked examples. It also names the sibling alternative (deep_research) and the condition that selects it (broad/multi-part questions needing fan-out), and clarifies news-routing 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 cover read-only, idempotent, open-world, and non-destructive behavior. The description adds meaningful behavioral context beyond that: it is a full working router with no fallback, behavior may change when a candidate routing variant is under test, and currently no candidate is active so it matches the stable version exactly. This is valuable dynamic-behavior disclosure.

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

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

The description is compact and front-loaded with the key distinction (beta of ask_pipeworx). Each sentence adds useful context, though there is mild redundancy between 'identical universal router' and 'Use it exactly like ask_pipeworx'.

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 universal router with no output schema, the description covers the essentials: it behaves identically to ask_pipeworx, returns the same response shape, is fully functional, and may have experimental routing changes. The current no-candidate state is also noted, which prevents an agent from assuming unusual behavior. It could mention the grounded sibling but does not need to for correct invocation.

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

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

Schema description coverage is 100%, with all parameters documented as aliases for 'question'. The description only says 'same arguments' without adding any new parameter detail. Since the schema carries the full semantic load, 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 states clearly that this is a beta version of ask_pipeworx with the same tools, arguments, and response shape, while adding experimental routing improvements. It references a specific sibling (ask_pipeworx) and explains how they differ, so an agent can confidently distinguish 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 directive: 'Use it exactly like ask_pipeworx when you want the newest routing.' It names the alternative and the condition favoring this beta tool. It does not explicitly state when not to use it, but the beta/experimental framing implies caution.

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, and non-destructive hints, so the safety profile is known. The description adds significant behavioral context beyond that: it guarantees extraction only from tool results, defines explicit refusal reasons, discloses the extra LLM call cost, and describes the return shape. There is no contradiction with the annotations.

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

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

The description is front-loaded with the core purpose and is information-dense, covering routing, grounding, refusal modes, use cases, and cost trade-off without wasted filler. It is slightly longer than strictly necessary, but each sentence contributes meaningful selection or invocation guidance.

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 return contract, failure/refusal behavior, selection criteria, and the trade-off against the sibling tool. Even though there is no output schema, the description itself provides the response shape and refusal reasons, so an agent has what it needs to invoke the tool correctly and interpret results.

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 documented in the input schema, including aliases for the question parameter. The description does not add parameter-level detail beyond what the schema provides, so the baseline 3 is appropriate.

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

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

The description uses a specific verb and resource: a 'hallucination-resistant answer mode' that routes like ask_pipeworx but extracts answers only from tool results. It explicitly distinguishes itself from the sibling ask_pipeworx by emphasizing groundedness and refusal behavior, 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 gives explicit when-to-use guidance: whenever an answer will be quoted, cited, or acted on, and when facts must not be invented (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative preference, saying to prefer ask_pipeworx for casual lookups because this mode costs one 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 reveals extensive behavioral details beyond annotations (which already set readOnly, openWorld, idempotent, non-destructive). It explains the resolution process (resolver contract with confidence levels, market_match_alternatives), classifier fan-out with specific example data packs, response shapes (market, analysis, evidence fields), safety features (low_confidence_match short-circuit, market_closed_or_inactive handling, illiquid_wide_spread), and resolution-rule risk (cancellation_rule details). No contradictions with annotations found.

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

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

The description is very lengthy and dense, covering many edge cases and examples. While all content is relevant, the text is not front-loaded efficiently; key information like response shapes and resolver contract is buried later. The description could be more concise by summarizing state machine flows (e.g., 'If low confidence, returns status:low_confidence_match') instead of full prose. Some redundancy across examples exists.

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

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

Given the complexity of the tool (multiple classifiers, fan-out to varied data sources, resolver logic, parent events, news fields, safety behaviors, closed market handling, spread warnings, cancellation rules) and no output schema, the description covers all critical aspects. It provides enough detail for an agent to understand input processing, response structure, and error paths. The inclusion of explicit fan-out examples and cancellation rule parsing fills gaps that would otherwise require external knowledge.

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% (all 3 parameters described), so baseline is 3. However, the description adds significant meaning beyond the schema's field descriptions: for `market`, it details accepted formats (slug, URL, question text); for `depth`, it defines 'quick' vs 'thorough' with source count; for `include_raw`, it explains size implications and when to set true. These concrete usage semantics substantially enhance 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 begins with a clear, specific verb-resource pair: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It explicitly names the resource (Polymarket bet) and the action (research using Pipeworx data). The description distinguishes this tool from siblings like polymarket_edges and polymarket_arbitrage by being the general-purpose research tool; no sibling overlaps directly, and the description implies it covers all bet types.

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: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It gives positive guidance on when to use the tool. However, it does not explicitly contrast with sibling tools (e.g., polymarket_edges for specific edge analysis) or state when NOT to use it. The lack of exclusion criteria prevents 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?

The description adds significant behavioral detail beyond the annotations (readOnlyHint, etc.): it explains data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handling of off-calendar fiscal years, sorting by primary metric, and the inclusion of citation URIs. No contradiction with annotations.

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

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

The description is somewhat lengthy but efficiently packs essential information. It is front-loaded with example queries and clearly structured. Minor redundancy (e.g., 'side-by-side comparison' appears twice) but overall well-organized.

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

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

No output schema, but the description mentions 'Returns paired data + pipeworx:// citation URIs per entity', which gives a sufficient hint about the return format. It could be slightly more explicit about the structure of the data, but given the complexity, it is fairly 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 description provides rich semantics for both parameters. It explains that type 'company' pulls latest 10-K financials and type 'drug' pulls FAERS and trial data. For values, it specifies tickers/CIKs for company and drug names, and the allowable range (2-5 items). This goes well beyond the schema descriptions.

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

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

The description clearly states the tool's purpose: performing side-by-side comparisons of 2-5 companies or drugs in one call. It provides example queries like 'compare X and Y' and 'rank these companies', and distinguishes itself from sibling tools like entity_profile by emphasizing it replaces sequential 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 explicitly advises to 'ALWAYS PREFER over sequential single-pack lookups when comparing entities', which is a strong usage guideline. It does not specify when not to use it, but the context is clear enough for most cases.

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

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

Annotations already mark this read-only, open-world, idempotent, and non-destructive, and the description adds substantial behavioral context beyond them: account/auth requirements, paid depth tier, structured-data-only behavior, parallel decomposition, gaps[] for unanswered facets, contradictions[], citation_uri fetchability, semantic excerpting, and latency expectations. No contradiction with annotations.

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

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

The description is long, but it is front-loaded with the most decision-critical information (account requirement, alternative tool, NOT open-web) and nearly every sentence adds a unique behavioral detail. It is slightly repetitive around contradictions[] and hop mechanics, but the density of useful information justifies the length.

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

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

Despite having no output schema, the description thoroughly explains the return shape: verbatim evidence, confidence, source, fetched_at, pipeworx:// citation, gaps[], contradictions[], hop field, and citation_uri. It also covers auth, depth tiers, latency, and when to choose a sibling tool, so an agent has everything needed to invoke it correctly.

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

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

Schema coverage is 100%, but the description still adds meaning: it expands the depth enum into concrete facet counts and hop behavior (quick=3, standard=3 with gap-recovery, thorough=6 with iterative follow-up), and clarifies that the question parameter supports broad/multi-part natural language. This goes well beyond the schema.

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

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

The description states a specific verb and resource: grounded multi-source research across Pipeworx's 1494 structured data sources, with decomposition and parallel routing. It also explicitly distinguishes itself from open-web search and from the single-lookup sibling ask_pipeworx, so an agent can tell it 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?

It explicitly says when to use this tool: 'Best for broad/multi-part questions over structured data' with concrete examples. It also gives exclusions and alternatives: 'For a single lookup use ask_pipeworx instead' and 'If you are not signed in, use ask_pipeworx instead'.

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

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

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds that it returns 'top-N most relevant tools with names, descriptions, and full input schemas (with curated examples)', and that each result is 'ready to call directly, no second schema lookup needed.' This provides useful behavioral context beyond the annotations, such as the structure of results and their reusability.

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

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

The description is moderately concise with several sentences, each serving a distinct purpose: defining the action, listing domains, describing output, and giving usage directive. It is front-loaded with the core purpose. While it could be slightly tighter (e.g., the list of domains is lengthy), it remains efficient and 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?

Given the tool has no output schema, the description compensates by explaining the output structure (top-N tools with names, descriptions, and full schemas with examples) and emphasizes that results are callable directly. With 6 parameters all documented in the schema, the description provides sufficient completeness for an agent to understand what to expect.

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 schema already documents all parameters adequately. The description does not add new parameter-level information beyond the schema, but it provides high-level context that the 'query' parameter accepts natural language descriptions. At baseline, a score of 3 is appropriate since the schema handles parameter semantics fully.

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

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

The description explicitly states the tool is for 'discovering' or 'finding' tools by describing a task or data, with a specific verb ('Find') and resource ('tools'). It distinguishes itself from sibling tools by advising to call this tool first when many tools are available, implying it's for exploration rather than direct action.

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

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

The description clearly indicates when to use the tool: 'when 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.' It provides context for using it as a preliminary step, but does not explicitly state when not to use it, though the 'first' directive implies 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 declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds behavioral context: fans out across multiple sources, mentions patents API sunset May 2025 (soft-fails), and details return fields. 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 a dense single paragraph with many examples and details. It could benefit from bullet points or clearer structure, but it is not overly long and remains 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?

Given the tool's complexity (multi-source, many return fields) and no output schema, the description enumerates all key return values and limitations (e.g., patents sunset, name requirement), providing sufficient completeness.

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

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

Schema coverage is 100% so baseline is 3. Description adds context like 'names not supported' and future plans for type, going slightly beyond schema, justifying 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 explicitly states the tool provides a full cross-source profile of US public companies, with specific examples like 'Tell me about X' and lists return fields. It distinguishes from sibling tools like resolve_entity and compare_entities.

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

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

Explicit guidance to prefer this tool over chaining single-pack lookups for holistic views, and to use resolve_entity first if only a name is available, clearly indicating when-to-use and when-not.

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 destructiveHint=true. Description adds context about clearing stale or sensitive data, which is valuable. No contradictions.

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

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

Three sentences, each purposeful: purpose, usage guidance, sibling pairing. No unnecessary words.

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

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

Complete for a simple tool with one parameter. Mentions when to use (stale/done/sensitive) and pairs with related tools. No missing information.

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

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

Single parameter 'key' with schema description 'Memory key to delete'. Description adds no further meaning. Schema coverage is 100%, so baseline 3 is appropriate.

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

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

Clearly states 'delete a previously stored memory by key'. Specific verb (delete), resource (memory), and method (by key). Distinguishes from siblings 'remember' and 'recall'.

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

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

Explicitly states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also implies alternatives by naming 'remember' and 'recall'.

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

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

Annotations already indicate readonly, idempotent, non-destructive behavior. The description adds transparency by explaining it fetches the page, extracts content, and emits markdown, disclosing the network call and processing steps 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 well-structured: opens with the core action and output, follows with process details, and ends with use cases. It is front-loaded and informative, though slightly verbose with redundant output format mention.

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

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

The tool has only 2 parameters, no output schema, and simple return (text blob). The description covers the process, output format, and use cases adequately. Missing error handling details but complete for typical usage.

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

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

With 100% schema description coverage, the schema already documents both parameters. The description rehashes the default and max for max_links, adding no new semantic value beyond clarifying that url is a full URL. Baseline 3 is appropriate.

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

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

The description clearly states the tool generates a production-ready llms.txt file for any URL, specifically for AI crawlers. It details the process (fetches page, extracts title/description/links) and output format, and distinguishes from siblings by focusing on llms.txt generation.

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

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

The description explicitly lists use cases: indexing a client's site, drafting for own project, auditing competitors. While it doesn't mention when not to use or compare with all siblings, it provides clear practical contexts for use.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds return fields and parameter behavior, enhancing transparency.

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

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

Two concise sentences with clear front-loading. No extraneous words.

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

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

No output schema but description lists key return fields. Context signals show simple structure; description is sufficient.

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 single parameter is well-described in schema. Description adds no extra semantic info beyond schema.

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

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

The description clearly states 'List the caller's active subscriptions' with a specific verb and resource. It distinguishes from sibling tools 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?

Explicitly advises use 'before adding more or to find an id to cancel', providing clear context. No explicit alternatives but implied by siblings.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds context by specifying the data is 'long-term monthly average,' implying historical data without real-time updates. 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?

One sentence of 12 words, front-loaded with key output. Every word is meaningful; 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?

Adequate given the output schema exists and annotations are rich. However, the description could mention data source or date range defaults. For a 7-parameter tool, slightly more context would help.

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

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

With 71% schema description coverage, the schema already documents most parameters. The description adds no new parameter details beyond the resource type. 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 the tool returns 'long-term monthly average global / diffuse / direct irradiation on horizontal / inclined plane,' specifying the resource type and orientation, distinguishing it from siblings like `tmy` (weather data) and `pv_performance` (system output).

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

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

No explicit guidance on when to use this tool versus alternatives (e.g., `tmy` or `pv_performance`). The description lacks context about appropriate use cases or exclusions.

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

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

Annotations are all false, so the description carries full burden. It discloses that this is a write operation (sends feedback), returns a claim_token when no account, and that the same token can be reused later to read resolution status. It also reveals rate limiting (5/day) and that it does not count against quota, going well beyond the annotation signals.

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?

Every sentence serves a purpose: purpose, classification, scope limitation, formatting advice, claim_token behavior, team responsiveness, rate limits, and quota info. It is front-loaded with the core purpose and immediately clarifies usage. No fluff or redundancy.

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

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

Despite having no output schema, the description covers the return claim_token, how to independently query it later, and operational constraints (daily reads, roadmap impact, rate limits). It accounts for the nested context object and the four distinct parameters, making the tool fully understandable.

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

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

Schema covers all 4 parameters, but the description adds semantic depth: it explains the claim_token format ('pwfb_…'), how to use it for follow-up, and gives examples of pack/tool/vertical context. It also enriches message guidance with specificity and length expectations, beyond the schema's one-line 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 opens with a specific verb+resource: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It clearly identifies the tool's purpose (sending feedback about Pipeworx tools) and distinguishes it from sibling tools by scoping exclusively to Pipeworx-provided tools, not 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 guidance: bug (wrong/stale data), feature/data_gap, praise. Also gives a clear exclusion criterion: do not report tools from other MCP servers. It even advises how to phrase feedback (in terms of Pipeworx tools/packs, not end-user prompts) and explains the claim_token follow-up mechanism, plus rate limits.

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

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

Adds significant context beyond annotations: explains data source (CF analytics-engine), privacy (no PII), caching behavior (5min-1h), and aggregation nature. No contradiction with annotations.

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

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

Four well-structured sentences: purpose, return list, use cases (bullet-style), data source & caching. Front-loaded with core purpose, no fluff.

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

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

For a simple read-only tool with one optional parameter, the description adequately explains output structure (tools, packs, volume), caching, and data source. No output schema needed given the clarity.

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 documents the parameter with enum and description. The tool description mentions window variants but adds no additional meaning or usage details 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 returns 'top tools, top packs, and total call volume over a recent window', with specific verb 'calling' and resource 'Pipeworx'. It distinguishes from sibling tools like 'discover_tools' by focusing on trending/popularity data.

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

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

Provides three explicit use cases (discovering hot data, confirming canonical tool, aligning use case). While it doesn't explicitly say when not to use it or name alternatives, the context is clear and actionable.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true. Description adds behavioral details: response structure, partition filter with placeholder logic, fill check warning not to trade if realizable edge ≤ 0, and explanation of cross-event mode limitations.

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 thorough but well-structured: general purpose, then mode-specific instructions, then details on filters and fill check. Every sentence adds value, though slightly verbose.

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 complexity (2 params, no output schema, rich behavior), the description covers output format, fill check, partition filter, and similarity threshold. No critical 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 covers 100% of parameters. Description reinforces and adds semantics: explains slug format, URL acceptance, and when to use each parameter (e.g., 'use this if you know the specific Polymarket event').

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 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It distinguishes three modes (no args, event, topic) and specifies the resource and actions.

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

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

Explicit guidance: 'Call with NO args for a trending_scan... pass event for the strongest per-event partition_check, or topic for a themed cross-event scan.' Recommends event mode and mentions custom sizing via polymarket_fill_risk.

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 annotations by detailing caching (1h), response structure (by_segment and diagnostics), edge calculation with slippage and Kelly fractions, special handling of Fed bets, and 24h move warnings. There is no contradiction with annotations.

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

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

The description is verbose and dense, with significant detail on model families and internal logic. While it is well-structured, it could be trimmed without losing essential information for an AI agent.

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 response structure including segments, edge fields, and diagnostics. It covers all aspects a caller needs to understand the tool's behavior and interpret results.

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

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

All 9 parameters have schema descriptions (100% coverage), but the tool description adds value by explaining practical usage scenarios for each knob (e.g., setting min_liquidity to drop thin books). This provides context 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: scanning top Polymarket markets and returning opportunities where Pipeworx data disagrees with market price. It uses a specific verb ('scan') and resource ('Polymarket markets'), and distinguishes from siblings like polymarket_arbitrage by focusing on model-driven discovery rather than pure arbitrage.

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 the tool ('what should I bet on today' context) and provides extensive guidance on knobs and filters. However, it does not explicitly state when to prefer sibling tools like polymarket_arbitrage or polymarket_edge_tracker, which would improve clarity.

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

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

The description extensively details behavioral traits beyond annotations: it explains snapshot-based telemetry, decay computation, trend classification, expired opportunities, and limitations like 60-day TTL. This far exceeds the minimal disclosure already provided by readOnlyHint and other annotations.

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

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

The description is well-organized with clear sections for inputs, response structure, and limits. It is verbose but every sentence adds value; minor structural improvements could make it more scannable.

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

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

Given the tool's moderate complexity and full schema coverage, the description is completely adequate. It covers input defaults, output fields, edge cases (expired, gaps), and historical constraints, leaving no significant 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%, so the description does not need to add much. It confirms defaults and explains window families, but provides no critical new meaning beyond the schema's own descriptions.

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

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

The description clearly states the tool's purpose: tracking edge persistence and decay over time using daily snapshots. It distinguishes itself from siblings by focusing on the temporal dimension, answering whether an edge is shrinking or has existed for weeks.

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

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

The description implies the tool is used when edge age matters, but it does not explicitly state when to use versus alternatives like polymarket_edges. No direct comparison or conditions are provided, leaving usage context somewhat inferred.

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 substantial behavioral context beyond annotations: walks the ladder, returns specific fields (top_of_book, vwap_fill_price, slippage_pp, etc.), and warns about forced directional risk and partial fills. Annotations confirm read-only, idempotent, non-destructive behavior, which is consistent.

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 sections and key terms in uppercase, but could be slightly more concise. However, every sentence adds value and is front-loaded with critical usage guidance.

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?

Fairly complete given complexity and no output schema: explains two modes, return fields, risk warnings. Minor gap: doesn't explicitly state behavior when neither market nor event is provided, but it says 'REQUIRES one.' Overall thorough.

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

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

Schema description coverage is 100%, and the description adds meaning by explaining side defaults, size_usd interpretation in both modes, and the market vs event distinction. It also clarifies auto behavior for basket side parameter.

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

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

The description clearly states the tool performs a realizable-vs-theoretical edge check against live CLOB order-book depth, distinguishing between single-market and basket modes. It uses specific verb-resource combinations and differentiates from siblings like polymarket_arbitrage and polymarket_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?

Explicitly states when to use: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' Explains rationale about theoretical overround on thin books and risk of partial basket fills converting arb into directional position.

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 read-only/idempotent annotations, the description discloses pairing behavior (unknown legs are never paired, land in skipped_unclassified/low_confidence_pairs), response safety fields (compatibility_warning/codes can be non-empty even with matched pairs), and the temporal_alignment/skipped counters. This is substantial behavioral context 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 clearly signposted with TWO MODES, RESPONSE, SAFETY FIELDS, Codes. It is front-loaded with the core purpose and each block adds distinct information. A 5 would require tighter prose; the density is justified by the tool's complexity, so 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 carries the burden of explaining return values, and it does: it names leg prices, top_spreads_pp, compatibility fields/codes, temporal_alignment, skipped counters, and the semantics of each code. It also warns about current reliability. Nothing essential for a correct call is missing.

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

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

Schema coverage is 100%, so the schema already documents all three parameters. The description adds value by explaining the two modes and how topic relates to the explicit kalshi_event_ticker/polymarket_event_slug overrides, which gives the agent a semantic model for parameter combinations beyond individual field 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 first sentence states a specific function: computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. The 'cross-venue' framing and Kalshi/Polymarket pairing distinguish it from the Polymarket-only siblings, and the two-mode description further clarifies what it 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 clearly explains two invocation modes (topic shortcuts vs explicit ticker/slug) and includes limitations such as 'pre-mapped ≠ tradeable' and the warning that most pre-mapped topics return compatibility_warning today. It does not explicitly name sibling alternatives or say when not to use this tool, so it stops short of 5.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to restate those. It adds minimal context by stating the tool 'models' and 'returns' output, which is consistent with annotations. No contradiction noted. However, it could mention that the tool does not modify any data or have side effects, but the annotations suffice.

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 extremely concise, consisting of two short sentences that front-load the core purpose and output. No extraneous information is included.

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

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

Given the tool has 8 parameters and an output schema, the description is minimal but covers the fundamental purpose and return format. It could provide more context about the modeling methodology or system parameters, but the output schema compensates for missing return details. Overall adequate for a straightforward read-only modeling tool.

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

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

Schema description coverage is 100%, with all 8 parameters already well-documented in the input schema. The description adds no additional meaning or context for the parameters, so it meets the baseline of 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 models annual and monthly PV system output, returning kWh/year estimates and monthly breakdowns. The verb 'Model' and resource 'PV system output' are specific, and it implicitly distinguishes from siblings like monthly_radiation and tmy by focusing on output rather than radiation or typical weather.

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 lacks any guidance on when to use this tool vs. alternatives. It does not mention when to choose this over sibling tools like monthly_radiation or tmy, nor does it specify any prerequisites or context for use.

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

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds context about scoping to an identifier and pairing with remember/forget, which complements 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?

Three sentences, front-loaded with the primary action, followed by use case, scope, and pairing. No wasted words.

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

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

Given no output schema, the description doesn't detail the return format, but the tool is simple. It covers the main behavior, parameter, and scope adequately.

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

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

Schema coverage is 100% with a good description of the key parameter. The tool description adds meaning by explaining the behavior of omitting key (list all keys) and provides examples.

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

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

The description clearly states the tool retrieves a value by key or lists all keys if omitted. It distinguishes itself from siblings by explicitly mentioning pairing with 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 the tool (look up stored context) and mentions alternatives (remember, forget). It lacks explicit when-not scenarios but is otherwise 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 mark it as read-only, idempotent, and non-destructive. The description adds valuable context: it reads from a persisted feed, returns specific fields, and mark_read modifies read state. 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 concise (4 sentences), well-structured, and front-loaded with the main action. 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?

Given 5 optional parameters and no output schema, the description adequately explains return fields, filtering, and state change behavior. It mentions the alternative HTTP endpoint, which adds completeness. Minor gap: no mention of pagination for limit handling beyond the 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 covers 100% of parameters with descriptions. The description adds meaning with examples (e.g., 'sec_8k' for type, ISO timestamp for since) and clarifies the effect of mark_read. This goes beyond schema.

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

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

The description clearly states the tool pulls fired events from the subscription feed, with specifics on return fields and filtering options. It distinguishes itself from sibling tools by focusing on recent alerts 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?

The description provides usage context (polls work fine, alternative HTTP endpoint for scripts) and explains the mark_read parameter for polling workflows. However, it doesn't explicitly contrast with siblings like list_subscriptions or search tools.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral details: it fans out to multiple sources (SEC EDGAR, GDELT→GNews, USPTO), explains fallback logic, soft-fail for patents, and the return structure (changes[] grouped by source + total_changes + citation URIs). No contradictions.

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

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

The description is comprehensive but somewhat dense as a single paragraph. It front-loads example queries and key behaviors, but could benefit from structured formatting (e.g., bullet points). However, every sentence adds value and it avoids redundancy.

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

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

Given the tool's moderate complexity (3 parameters, no output schema), the description fully covers all critical aspects: data sources, fallback behavior, date formats, sibling differentiation, and the structured return format. It leaves no gaps for an AI agent to misinterpret.

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 each parameter described. The description adds meaningful context beyond schema: for 'since' it explains ISO date vs relative shorthand ('7d', '30d', '3m', '1y') and recommends '30d' or '1m' for monitoring; for 'value' it provides examples (ticker or CIK); for 'type' it clarifies only 'company' is supported. This significantly aids correct invocation.

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

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

The description explicitly states the tool returns a change feed (SEC filings, news, patents) for a company over a recent time window. It includes example queries like 'What's new with X' and distinguishes from the sibling tool entity_profile, making the purpose crystal 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?

The description provides explicit guidance on when to use this tool (e.g., 'latest on Y', 'what happened to Z') and when to use entity_profile instead ('when you want the static profile regardless of window'). It also explains the fallback mechanism and accepted date formats, leaving no ambiguity.

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

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

Discloses beyond annotations: scoped by identifier, persistent for authenticated users, 24-hour retention for anonymous. Annotations show idempotentHint=true and destructiveHint=false, consistent with description. 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 descriptive paragraph with front-loaded purpose, no wasted sentences. Every sentence adds value (usage, behavior, lifecycle).

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 key-value store with no output schema, description covers purpose, usage, parameter semantics, persistence, and integration with recall/forget. Complete for agent invocation.

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

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

Schema coverage is 100% with descriptions, so baseline is 3. Description adds examples of key names and value content, reinforcing purpose but not adding new structural meaning beyond schema.

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

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

Clearly states the tool saves data for reuse (verb+resource), distinguishes from sibling tools like recall and forget by mentioning them, and provides concrete usage examples (resolved ticker, target address, etc.).

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

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

Explicitly tells when to use: when discovering something worth carrying forward, with examples. Mentions pairing with recall/forget for lifecycle management. 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?

Annotations already mark it as read-only, open-world, idempotent, and non-destructive. The description adds significant behavioral detail: internal cascading lookups, graceful degradation if GLEIF/OpenFIGI are unavailable, explicit handling of unresolved identifiers, and labeling of sources. This goes well beyond annotations.

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

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

The description is front-loaded with example queries, well-structured into sections for use, types, and degradation. However, it is somewhat verbose with detailed nested explanations (e.g., LEI/FIGI enrichment details). Slightly more concise would improve it, but it remains organized and readable.

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

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

Given the tool's complexity (two parameters, no output schema), the description covers purpose, input handling, and output expectations (identifiers with sources, unresolved list). It lacks explicit return format details but is sufficient for an agent to use the tool correctly. Graceful degradation and multi-step cascading are explained well.

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

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

Schema coverage is 100%, but the description adds substantial meaning: it explains what each `type` option entails (e.g., company includes CIK, ticker, LEI, FIGI; accepts ticker, CIK, ISIN, name) and what `value` expects. It also describes resolution logic and output structure, far exceeding basic schema info.

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

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

The description clearly states the tool resolves names to canonical identifiers, provides exhaustive example queries, and explicitly differentiates it from siblings by saying 'Use FIRST whenever you have a name but need an ID.' The supported types are listed with detail, making the purpose 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 gives explicit guidance: 'Use FIRST whenever you have a name but need an ID.' This sets clear context. It does not explicitly mention when not to use it or name alternative sibling tools, but the guidance is strong enough for an agent to decide.

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, etc.), the description reveals that the tool probes each entity with ai_visibility_check, ranks by score, and returns a ranked list with score, confidence, and signal density. It does not contradict any 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 (three sentences), front-loads the action, then describes mechanics and use case. Every sentence is informative 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?

Given no output schema, the description partially compensates by naming return fields (score, confidence, signal density). It covers all essential aspects (purpose, usage, parameters, return type) but omits details like exact output structure and error handling.

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

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

All four parameters have descriptions in the input schema (100% coverage). The description adds value by explaining that the first entity is treated as the 'subject' for narrative, and that models defaults to workers-ai without _apiKey.

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: 'Compare AI visibility across multiple entities side-by-side.' It uses specific verbs ('probes', 'ranks', 'surfaces') and distinguishes itself from sibling tools like ai_visibility_check (single entity) and compare_entities (general comparison).

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

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

The description provides clear usage context: 'Useful for competitive AI-marketing audits: does Claude know about us as well as our competitors?' It implies when to use (multi-entity comparison) but does not explicitly exclude alternatives or state when not to use it.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: bundlephobia's first measurement can take 5-30s, sources_failed lists timeouts, partial failures degrade gracefully. 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 front-loaded with the core purpose and packs significant detail into two paragraphs. While not ultralight, every sentence adds value. There is no waste, but could be slightly tighter without losing 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?

No output schema is provided, so the description must explain return values. It does so thoroughly, listing all fields in the summary block, advisory details, links, and alternative versions. It also covers edge cases like partial failures and timing, making the tool's behavior fully understandable.

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 includes descriptions for both parameters. The description adds minimal extra meaning beyond the schema, such as mentioning scoped packages and default version behavior, but it does not compensate for any gaps since there are none. Baseline 3 is appropriate.

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

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

The description clearly states the tool's verb and resource: 'Composite should I add this npm package to my project check in ONE call'. It distinguishes from siblings by noting that the tool only covers the NPM ecosystem, and for other ecosystems to use deps.dev directly.

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 specifies when to use: 'Use whenever an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me''. Also provides exclusions: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly'. This is clear and actionable.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds character offsets, similarity scores, BGE-base-en embeddings + cosine over 500-char windows, and a 200K char cap with truncation flag. 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 approximately 100 words, well-structured into two paragraphs: first explains core functionality and use case, second adds technical details. Front-loaded with main purpose. No unnecessary sentences.

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 mentions return type ('passages with character offsets and similarity scores') and covers constraints (200K char cap, truncation flag). Pairs well with sibling tool. Complete for this 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 description coverage is 100%, so baseline 3. Description adds minimal extra: for text, 'max ~200K chars' (redundant with schema); for query, provides examples; for limit, mentions default 5. Does not significantly enhance meaning beyond schema.

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

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

The description clearly states 'Semantic search INSIDE a fetched record' with the verb 'search' and resource 'record'. It distinguishes from siblings by mentioning it pairs with ask_pipeworx_grounded and contrasts with fetching the whole document.

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 the record is too big to cram into the prompt' and explains benefits like saving context and verifiable quotes. Mentions an alternative tool (ask_pipeworx_grounded) for grounding.

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 mutation (readOnlyHint=false), idempotence (idempotentHint=true), and non-destructiveness (destructiveHint=false). The description adds context: returns new ID, delivery channels, webhook auto-disable, and account requirements. 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 front-loaded with the main purpose and progressively details types and delivery. It is somewhat verbose but each sentence contributes meaning; minor redundancy on delivery channels.

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

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

Given no output schema, description covers return value ('Returns the new subscription id'), type-specific parameters, and delivery details. It lacks explicit indication of response format but is adequate for a creation tool.

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

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

Schema coverage is 100%, baseline 3. Description adds value with type-specific examples (e.g., sec_8k items, polymarket_edge topic) and delivery constraints (sms verification, webhook signing). However, it omits examples for patent_grant and clinical_trial types present 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?

The description clearly states it creates a proactive monitoring subscription to a live-data event stream and returns a subscription ID. It distinguishes itself from sibling tools like list_subscriptions and unsubscribe by focusing on creation.

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

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

The description specifies requirements (Pipeworx OAuth account), provides supported types with examples, and details delivery channel limitations (SMS verification, daily cap). However, it does not explicitly warn against misuse or compare to alternatives like anonymous subscriptions.

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. The description adds valuable context: it returns example questions, draws from a live catalog, and is the entry point. No contradictions. Adds some behavioral insight beyond annotations.

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

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

The description is somewhat long but front-loaded with key info. Every sentence serves a purpose, listing categories and usage guidance. Could be slightly more concise, but remains effective.

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

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

For a tool with one optional param and no output schema, the description fully explains what the tool returns (category-bucketed example questions) and its purpose (onboarding). Complete for its 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% with one optional parameter. Description elaborates on the 'topic' parameter by listing valid focus areas (finance, pharma, etc.) and explaining that omitting it yields a cross-category spread, adding meaning beyond the schema's description.

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

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

The description clearly states the tool serves as the onboarding entry point, returning category-bucketed example questions with exact tool+argument shapes. It distinguishes itself from sibling tools by specifying when to use it ('when you do not yet know what Pipeworx can do for you').

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

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

Explicitly says 'Use this FIRST' when unfamiliar with Pipeworx or to learn how to call meta-tools. Mentions alternatives like ask_pipeworx, entity_profile, etc., providing clear context for when to use this tool vs. siblings.

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

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

Annotations thoroughly cover safety (readOnly, idempotent), so the description's burden is reduced. It adds that the output is an hourly synthetic year, but lacks details on rate limits, data sources, or limitations.

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 phrase, concise but overly terse. It front-loads the resource name but omits essential parameter and usage details, making it under-specified.

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 having an output schema, the description lacks parameter semantics, usage context, and behavioral details, making it incomplete for an agent to use correctly.

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

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

With 0% schema description coverage, the description must explain parameters but does not. No mention of latitude/longitude meaning or startyear/endyear time range.

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

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

The description identifies the resource as a Typical Meteorological Year, implying generation or retrieval of hourly synthetic climate data. This distinguishes it from sibling tools like monthly_radiation or pv_performance, though the verb is implicit.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or 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?

Adds key behaviors beyond annotations: ownership enforcement, row deactivation (not deletion), preservation of historical events. No contradiction with annotations (destructiveHint=false aligns with deactivation).

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 concise sentences, each adding unique value. Front-loaded action verb. No extraneous information.

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

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

Given simple tool (one param, no output schema), description fully explains effect, ownership, and persistence behavior. Complete for agent decision-making.

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

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

Schema coverage is 100% with clear parameter description. Description does not add further parameter semantics; baseline score appropriate.

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

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

Description uses specific verb 'Cancel' and resource 'subscription by id'. Clearly distinguishes from sibling tools like 'subscribe' and 'list_subscriptions'.

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

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

States ownership enforcement and deactivation behavior, implying it's for canceling own subscriptions. No explicit when-not-to-use or alternative guidance, 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 well beyond the read-only/idempotent annotations by disclosing the two-pipeline routing (SEC vs grounded), the exact verdict vocabulary, and the crucial semantics of 'could_not_verify' (i.e., the check did not happen and must not be treated as evidence) and 'unsupported' (no source exists). It also mentions the return of verbatim evidence with citations and the fact that it replaces multiple sequential calls.

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 densely packed with useful information—query examples, routing logic, output structure, and important caller warnings—yet every sentence earns its place. It is organized into clear sections and avoids redundancy or fluff.

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

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

Even without an output schema, the description fully covers the return values (verdict types, actual value with citation, reasoning), explains error semantics, and covers both financial and non-financial claim paths. An agent has all necessary context to invoke the tool and interpret results 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 provides thorough descriptions for both parameters: 'claim' with a concrete example and 'tolerance_pct' with its overrides, default, and range (0.5–50). With 100% schema coverage, the description adds little new meaning to the parameters themselves; it only indirectly references percent-delta math in the financial path. This matches the baseline of 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 identifies the tool as a natural-language claim verifier with explicit example queries ('fact check', 'verify the claim that…'). It distinguishes between company-financial claims routed to SEC EDGAR+XBRL and all other factual claims routed to a grounded pipeline, making its scope unambiguous and distinct from sibling research/search 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 states an explicit when-to-use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also clarifies that every factual claim automatically falls into one of two paths, implying coverage of all verification needs. However, it does not explicitly name alternatives or provide 'when-not-to-use' conditions, so it falls short of a 5.

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