Unicef

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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds significant context: it probes LLMs, returns scores with confidence/signals, details default model versus Anthropic (BYO key, direct payment), and confirms 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 concise (two sentences plus brief explanations) and front-loaded with the main purpose. It could be slightly more structured, but it is not overly verbose and each sentence adds value.

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

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

Given no output schema, the description explains the return format (per-model {score, confidence, signals, raw_response} + combined view). All four parameters are covered with meaningful context, and the tool's purpose is fully explained 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 description coverage is 100%, so baseline is 3. The description adds value by clarifying the default model ('workers-ai' is free), the role of '_apiKey' (BYO key and direct payment), and that 'context' helps disambiguate common names.

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

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

The description clearly states the tool probes LLMs for knowledge about an entity and scores visibility on a 0-100 scale. It uses a specific verb 'probe' and resource 'visibility', and distinguishes itself from siblings by its focus on AI visibility scoring for marketing audits.

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 use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and explains default model usage and optional Anthropic probing with API key. However, it does not explicitly exclude when not to use or compare to sibling tools like scan_competitor_ai_presence or entity_profile.

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 the safety profile (read-only, idempotent, open-world). The description adds meaningful behavioral context: it routes internally, fills arguments automatically, and returns structured answers with stable citation URIs. It doesn't discuss failure modes or limits, but given annotation coverage, this is a solid 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 front-loaded with the most important guidance and includes a dense but helpful list of domains, trigger phrases, and examples. It loses a point for minor run-on/formatting issues in the 'step up' section and for being slightly longer than necessary, 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 broad meta-tool with no output schema, the description covers routing behavior, citation guarantees, domain scope, example queries, and escalation paths to sibling tools. It doesn't specify the exact response shape, but the schema and examples provide enough for an agent to select and invoke the tool correctly.

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

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

Schema coverage is 100% with clear alias descriptions for all six parameters, so the description doesn't need to add parameter-level semantics. It does provide useful example phrasings for the question parameter, but that is marginal additional value beyond the schema's examples and 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 identifies the tool as a natural-language entry point that routes questions to one of 5,798 tools across 1,517 verified sources and returns structured answers with pipeworx:// citation URIs. It also explicitly frames itself as the preferred alternative to web search, which distinguishes it from sibling tools like ask_pipeworx_grounded and deep_research.

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

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

It gives explicit when-to-use instructions ('PREFER OVER WEB SEARCH', 'START HERE for most questions', 'Use whenever the user asks...'), provides concrete trigger phrases and example queries, and names the conditions for escalating to ask_pipeworx_grounded or deep_research. This is strong routing guidance with specific alternatives.

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

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

The description discloses beyond the annotations that this is an experimental beta edge, that candidate routing improvements may be live only when under test, that no candidate is currently active, and that it is a full working router with no fallback. This is rich behavioral context the annotations do not provide.

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

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

The description is information-dense and front-loads the core beta identity, then covers current status, usage, and experimental behavior. It is slightly repetitive around matching ask_pipeworx, but each sentence contributes useful context.

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

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

Given the simple alias-only schema, rich readOnly/openWorld/idempotent annotations, and the clear relationship to the ask_pipeworx sibling, the description covers everything needed to invoke the tool correctly. It states current routing state, usage instructions, and experimental behavior.

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

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

Schema description coverage is 100%, and the schema already documents all six string aliases for the question parameter. The description adds no parameter-specific meaning beyond noting the tool uses the same arguments as ask_pipeworx, so the baseline score of 3 applies.

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

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

The description clearly identifies the tool as a beta version of ask_pipeworx: a universal router with the same 5,798 tools, arguments, and response shape, but with candidate routing improvements. This differentiates it from the stable ask_pipeworx sibling and states exactly what kind of tool it is.

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 to use it exactly like ask_pipeworx when the agent wants the newest routing, and notes that results are compared against the stable router to decide what merges. This gives a clear selection condition and names the relevant alternative.

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

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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses the full behavioral contract: grounded extraction from tool results only, the exact success shape {answer, evidence, confidence, source, fetched_at, refusal_reason:null}, and explicit refusal with a complete refusal_reason enum. It also reveals the cost penalty (one extra LLM call), which annotations cannot convey.

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

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

Information-dense but front-loaded: the differentiator, mechanism, return shapes, usage rule, and cost tradeoff each earn their place. Minor deduction for the volatile specificity '5,798 across 1517 sources,' which risks staleness and is not essential to correct invocation.

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

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

Although the tool is complex (routing across thousands of sub-tools) and has no output schema, the description fully specifies both success and refusal return shapes, the verbatim-evidence guarantee, and cost/usage tradeoffs. The simple 1-parameter schema and safety annotations cover the rest. Nothing needed for correct invocation is missing.

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

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

Schema description coverage is 100% — the single required 'question' parameter and its six aliases are fully documented in the schema itself, so the description needs to add no parameter-level meaning. The description's mention of internal argument-filling is behavioral context, not parameter semantics. Baseline 3 applies.

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

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

The description opens with a specific, differentiating claim — 'Hallucination-resistant answer mode for high-stakes reads' — and explicitly contrasts with the sibling ask_pipeworx ('Same routing as ask_pipeworx... then EXTRACTS the answer using ONLY what the tool result contains'). An agent can immediately tell this apart from ask_pipeworx and ask_pipeworx_beta in the sibling list without opening their schemas.

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

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

Usage guidance is explicit and actionable: 'Use whenever an answer will be quoted, cited, or acted on' with concrete domains (financial verdicts, legal claims, medical lookups, public statements), and the tradeoff is stated — 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This gives both when-to-use and when-not-to-use with the alternative named.

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?

Goes far beyond annotations: fan-out mechanism, response shapes, status codes, blocking behaviors, resolution rule risk, and news backfill details are all disclosed. 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?

Very detailed but overly long and dense. Structured with headers but could be more concise. Every sentence adds value, but the length may overwhelm agents.

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

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

Covers all edge cases, response shapes, safety mechanisms, and cancellation rules. With no output schema, the description fully explains return structures and status fields. Nearly exhaustive.

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 good descriptions. The tool description adds context on defaults and usage recommendations (e.g., depth default, include_raw false). Adds moderate value 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 verb 'research' and the resource 'Polymarket bet', with explicit use cases ('should I bet on X', 'what does the data say about Y'). Differentiates from sibling tools like polymarket_edges by focusing on individual bet research with Pipeworx 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 explicit when-to-use scenarios and detailed operational notes (e.g., resolver contract, market closed handling, wide spread warnings). Guides the agent to inspect certain fields before trusting analysis.

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

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

Discloses behavioral traits beyond annotations: pulls latest 10-K data for companies, handles off-calendar fiscal years, sorts results by primary metric, uses SEC EDGAR/XBRL and FAERS, returns citation URIs. Annotations already declare readOnlyHint and idempotentHint, which the description supports 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 slightly verbose but well-structured with examples, clarifications, and behavioral notes. Every sentence adds essential information, making it mostly concise for the level of detail needed.

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

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

Despite no output schema, the description explains return format (paired data + citation URIs), covers both entity types, and addresses edge cases (off-calendar fiscal years). All relevant context for using the tool is provided.

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

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

Adds meaning beyond schema: for type, it specifies what data each type pulls (revenue, net income, etc. for companies; adverse-event counts for drugs). For values, it gives examples (tickers for company, drug names). This enriches the schema descriptions which were already present (100% coverage).

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

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

The description clearly states the tool does side-by-side comparison of 2-5 companies or drugs, with example phrases like 'compare X and Y' and 'rank these companies'. It distinguishes from sibling tools like entity_profile which do single-entity lookups, emphasizing it replaces 8-15 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?

Explicitly instructs to 'ALWAYS PREFER over sequential single-pack lookups when comparing entities'. Provides clear context that it is for comparisons and replaces many sequential lookups, giving strong usage guidance.

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

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

Annotations already fully declare read-only, idempotent, and non-destructive. Description adds context about how to interpret the output for building keys but no additional behavioral traits.

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 plus example; front-loaded with key purpose. Could be slightly tighter but overall efficient.

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

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

Completely describes what the tool returns, how to use the result, and when to call it. No output schema, but explanation suffices. Parameter is well-documented.

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

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

Schema already fully describes the parameter with example values. Description repeats the example and adds context about usage, but does not significantly extend beyond schema coverage.

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

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

Clearly states it gets the structure of a UNICEF dataset, specifying ordered dimensions and valid codes. Differentiates from siblings like get_data and list_dataflows by explaining its preparatory role.

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

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

Explicitly instructs to call before get_data and provides a usage example. 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?

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses account requirements, parallel tool routing, gap reporting with explicit gaps[], never-invented guarantees, contradiction detection, latency expectations, citation resolvability semantics, and excerpting behavior. This is rich, honest behavioral context that fully 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?

The description is long but justified by the tool's complexity. It front-loads the account requirement and routing alternative before diving into mechanics, and nearly every sentence adds operational detail. Minor redundancy and dense phrasing prevent a perfect score.

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

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

Despite having no output schema, the description thoroughly explains what the agent will receive: findings packets with evidence, confidence, source, fetched_at, hop, citation_uri, gaps[], and contradictions[]. It also covers timing, auth, paid tier, multi-pass behavior, and fallback routing, making the tool safe and predictable to invoke.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds value beyond schema by explaining that depth:"thorough" requires a paid plan, that the question can be broad/multi-part, and that standard/thorough include gap recovery and contradiction scans. This extra operational meaning helps the agent choose parameter values correctly.

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

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

The description clearly identifies the tool as grounded multi-source research over structured data, with a specific verb (research/decomposes), resource (1517 structured data sources), and explicit contrast to open-web search. It also names ask_pipeworx as the single-lookup alternative, making sibling differentiation explicit.

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

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

The description explicitly states when to use deep_research (broad/multi-part questions over structured data) and when not to (single lookups, or when not signed in, use ask_pipeworx). It even covers the paid-tier requirement for depth:"thorough", giving the agent clear routing guidance.

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

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

Annotations declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, indicating safe, read-only behavior. The description adds significant behavioral context: it returns 'the top-N most relevant tools with names, descriptions, and full input schemas (with curated examples) — each result is ready to call directly, no second schema lookup needed.' It also explains alias handling. No contradictions.

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

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

The description is two sentences: the first clearly states purpose and usage, the second explains the return value and strategic use. Every sentence is necessary and efficiently packed with information. No 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?

Given that the schema covers all parameters (100%) and no output schema is present, the description fully compensates by explaining exactly what is returned (names, descriptions, full schemas with examples) and that results are directly callable. It also mentions the default and max limit. For a tool of moderate complexity, this is complete.

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

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

Schema coverage is 100% with 6 parameters, many of which are aliases for 'query'. The description adds meaning by explaining that 'query' accepts natural language and that aliases like 'task', 'q', 'description', and 'search' are accepted. This clarifies usage beyond the schema, which only lists them as type string. However, the schema already provides descriptions for each alias. The additional value is moderate, so a 4 is appropriate.

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

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

The description clearly states the tool's purpose: 'Find tools by describing the data or task.' It lists numerous domains (SEC filings, financials, etc.) and explicitly distinguishes it from sibling tools by stating 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This makes the purpose unambiguous and distinct.

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

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

The description provides explicit usage guidance: 'Use when you need to browse, search, look up, or discover what tools exist for: ...' and 'Call this FIRST when you have many tools available and want to see the option set.' It implies when-not-to-use by contrasting with tools that provide just one answer. No alternatives are named, but the context is clear enough.

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

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

Annotations already mark the tool as readOnly, openWorld, and idempotent, so the bar is lower, but the description adds substantial behavior: it discloses the USPTO PatentsView API sunset with soft-fail behavior, clarifies that empty FDA sections are expected for small-molecule-only companies, and explains sources_used/sources_failed semantics. 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 the tool is genuinely broad, and almost every clause earns its place. It front-loads examples and the core purpose before the fan-out details. It could be better structured with bulleted return sections, but it is not padded.

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

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

There is no output schema, so the description carries the full burden of explaining return values. It enumerates each payload section (cik, recent_filings, fundamentals, patents, federal_contracts, fda_products, hiring, news, LEI) and even notes edge cases like 'empty section is a real no-data'. This is sufficient for an agent to invoke the tool 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 coverage is 100%, so the input schema already documents both parameters fully. The description reinforces that 'type' accepts 'company' or 'ticker' interchangeably and that 'value' can be a ticker, CIK, or name, but this mostly restates the schema rather than adding new semantic depth.

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 concrete user phrasings ('Tell me about X', 'brief me on Tesla') and then states the action precisely: 'full cross-source profile of a US public company in ONE parallel call.' It explicitly contrasts with chaining single-pack lookups, differentiating it from sibling tools that target a narrower scope.

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

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

It gives an explicit directive: 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also states accepted value shapes (ticker, zero-padded CIK, company name) and what happens for private companies or non-US entities ('person/place coming soon', 'resolved:false...not a bare failure').

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

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

Description aligns with annotations (destructiveHint=true, idempotentHint=true). Adds context about clearing sensitive data, though no behavioral nuance beyond annotations.

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

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

Two sentences front-loading purpose, no unnecessary words. Every sentence is 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?

For a simple single-parameter tool with annotations, the description is complete: states purpose, usage, and sibling tools. No gaps.

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

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

Schema coverage is 100% with parameter description 'Memory key to delete'. Description does not add extra meaning beyond schema; baseline score applies.

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

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

The description clearly states the tool deletes a previously stored memory by key, with a specific verb and resource. It distinguishes from siblings (remember, recall) as the deletion counterpart.

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

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

Explicitly provides when to use: when context is stale, task done, or to clear sensitive data. Mentions pairing with 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?

Description adds behavioral detail beyond annotations: explains fetching, extracting title/description/key links, and emitting standard markdown format. Annotations already indicate read-only, idempotent, non-destructive; description complements them without contradiction.

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

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

Three sentences, front-loaded with primary action, no filler. Every sentence serves a purpose: definition, process, use cases.

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

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

Covers purpose, process, output format, and usage scenarios. With only two parameters and rich annotations, the description is sufficient. Could optionally mention limitations (e.g., dynamic content), but not necessary for a non-destructive tool.

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

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

Schema coverage is 100% and both parameters are already well-documented in the schema. Description does not add extra meaning beyond what the schema provides (e.g., defaults repeated).

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

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

Clear verb+resource combination: 'generate a production-ready llms.txt file for any URL'. Distinct from sibling tools like scan_competitor_ai_presence, which focus on auditing rather than 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?

Explicitly lists three use cases (client indexing, own project drafting, competitor auditing) but does not specify when to avoid using or alternatives.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds behavioral context: the key parameter uses dot-separated wildcard filtering, the result can be large when no key is given, and the return includes decoded series with labels and per-period values. 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 concise, with two paragraphs and an example. It front-loads the main purpose and efficiently covers key usage details without excess. Every sentence adds value.

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

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

Given no output schema, the description adequately states what is returned (decoded series with dimension labels and per-period values). It covers prerequisites, parameter behavior, and a caution. Slightly more detail on response structure could be helpful, but sufficient for a read-only tool.

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

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

Schema coverage is 100% (all parameters described), baseline 3. The description adds substantial meaning beyond the schema: it explains the dot-separated SDMX filter format, the positional wildcard behavior, and provides an explicit example. This significantly aids correct usage.

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

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

The description clearly states 'Pull observations from a UNICEF dataset' specifying a specific verb ('pull') and resource ('UNICEF dataset'). It distinguishes itself from sibling tools like dataflow_structure by noting the prerequisite call.

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 advises calling dataflow_structure first to learn dimension order and valid codes, providing clear usage context. It also warns that omitting the key parameter can return a large dataset. However, it does not explicitly state when not to use this tool or list alternatives.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds that results have id, version, name, and there are ~70 datasets, but doesn't add significant behavioral traits beyond annotations.

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

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

Two well-structured sentences with examples, front-loaded with purpose, 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, description mentions result fields (id, version, name), scope (UNICEF, ~70 datasets), and connects to sibling tools, making it complete for a listing tool.

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

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

Schema coverage is 100%, baseline 3. Description adds usage examples and explains query as case-insensitive substring filter on id or name, also mentions default limit 50, adding value 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 is for browsing or keyword-searching UNICEF datasets (dataflows). It distinguishes from sibling tools by mentioning the 'id' is passed to dataflow_structure/get_data.

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

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

The description gives explicit usage with examples (passing query like 'mortality' or 'nutrition'), mentions ~70 datasets, and implies filtering. It lacks explicit when-not-to-use, but the examples and context are clear.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. Description adds context about return fields and inactive subscriptions, but bar is lower due to annotations covering safety.

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

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

Two sentences, front-loaded with purpose, no redundancy. Every sentence is essential and well-structured.

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

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

Given no output schema, the description lists return fields. Combined with strong annotations, it provides a complete understanding of the tool's behavior and output.

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 well-described parameter. Description adds value by listing the return fields (id, type, params, created_at, last_fired_at, fire_count), which the schema does not include.

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 lists active subscriptions and returns specific fields. It distinguishes itself from siblings like subscribe and unsubscribe by focusing on listing.

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 guidance: use to review subscriptions before adding more or to find an id for cancellation. This clarifies when and why to use this tool.

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

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

Annotations only indicate non-read-only, non-idempotent, etc., but the description adds rich behavioral context: rate-limited to 5 per identifier per day, free and doesn't count against tool-call quota, returns a claim_token when no account is used, and that the team reads digests daily. 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?

Though lengthy, every sentence serves a purpose: purpose, when-not-to-use, privacy guidance, token workflow, rate limits, and roadmap impact. The description is front-loaded with the core action and progressively adds operational details, without wordiness.

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

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

The tool has a nested object, an optional token, and no output schema, but the description covers all necessary context: what to write, how to reference tools, how to check resolution, limits, and that an account is not required. The absence of an output schema is compensated by explaining the claim_token return.

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

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

The schema already covers 100% of parameters, so baseline is 3. The description adds value by explaining the claim_token round-trip flow (pass it back later to read status), and advising not to paste the end-user's prompt, which complements the 'context' and 'message' fields. It also elaborates on the 'type' enum categories in plain language.

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 exactly what the tool does: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It clearly distinguishes this from sibling tools by specifying it is a feedback channel for Pipeworx tools, and even clarifies what it is not for (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?

Explicitly defines when to use: bug, feature/data_gap, praise, and 'other.' It also provides a clear exclusion: if the tool is from a different MCP server, file with that server instead. Additional guidance includes not pasting end-user prompts and using a claim_token for follow-up.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds valuable context: the data source (CF analytics-engine), no PII, and caching behavior (5min-1h). 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 compact, front-loads the main purpose, and each sentence adds distinct value (return type, use cases, data source, caching). No wasted words.

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

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

Despite no output schema, the description sufficiently describes the return (top tools, packs, total call volume) and caching behavior. A more explicit output structure would be ideal, but the current detail is adequate for an agent.

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

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

Schema coverage is 100% with an enum description. The description adds meaning by explaining the trade-off between windows: 'shorter windows surface what's hot right now; longer windows show steady-state demand', which helps agents choose appropriately.

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

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

The description clearly states the tool returns 'top tools, top packs, and total call volume over a recent window' with specific verb and resource. It distinguishes from siblings like 'discover_tools' by focusing on popularity metrics. The use cases further clarify its unique value.

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

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

Explicitly lists three useful scenarios (discovering hot data sources, confirming canonical tools, checking alignment). While it doesn't mention when not to use or alternatives, the context is clear and actionable for an AI agent.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds extensive behavioral detail: algorithms (monotonicity, partition checks), conditions for signal emission (deviation >3pp, similarity filter, placeholder filter), and fill check warnings. No contradictions.

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

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

The description is thorough and well-structured with sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK), but it is fairly long. While every sentence adds value, brevity could be improved slightly without losing meaning.

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

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

Given the complexity and lack of output schema, the description covers all necessary aspects: functionality, parameter behavior, response structure, edge cases (placeholder filter, similarity filter), and cross-tool references. It is complete for effective use.

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

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

Schema coverage is 100% and the description adds significant context: event parameter accepts slug or URL, topic parameter is a seed question. It explains the behavior for each parameter and how they affect scanning. This goes beyond the schema.

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

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

The description clearly states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes three modes: no args (trending_scan), event mode (single-event), topic mode (cross-event). This specificity and differentiation from siblings is excellent.

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

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

The description provides explicit guidance on when to use each mode, including recommendations ('event recommended for a specific market'). It also explains when not to trade (fill check). This is comprehensive 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 the tool as read-only, idempotent, and non-destructive. The description adds extensive behavioral context: caching strategy (1h at KV level), diagnostics fields to explain empty segments, Fed market handling, and the exact edge fields returned. 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 comprehensive and well-organized, but slightly verbose with some implementation details (e.g., specific alpha values, funnel counters) that could be omitted for brevity without losing value.

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

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

Given the complexity (three segments, multiple filters, output structure) and no output schema, the description fully covers the output format (by_segment, fed, diagnostics), caching, and edge fields. It also explains why certain opportunities are excluded (placeholder filters, Fed note).

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 having a description. The description further explains parameter interactions (e.g., min_kelly vs min_partition_leg_kelly, tradeable-edge filters). It adds real-world context like slippage assumptions and Polymarket zero trading fees.

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 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It distinguishes from siblings like polymarket_arbitrage by focusing on edge detection and explicitly targeting 'what should I bet on today' use case.

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 the tool is for discovering opportunities without paging through markets, and provides guidance on when to use various knobs (min_liquidity, max_spread_pp). It does not explicitly state when to avoid using the tool but context is clear.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and no destructive behavior. The description adds important behavioral details: data comes from daily snapshots written on cache-miss, gaps mean no scan, history bounded by 60-day TTL, decay computed from daily closes. 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 informative but slightly verbose, including example scenarios and detailed field explanations. It is well-structured with a clear flow from purpose to response fields to limits, but could be more concise.

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

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

With no output schema, the description thoroughly explains the response structure (tracked, expired, snapshot_dates) and field meanings. It also covers limits and data source, making it complete for an agent to understand the tool's behavior.

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

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

Both parameters are fully described in the schema (100% coverage). The description adds default values and explains the meaning of 'window' as snapshot family, which goes beyond schema repetition.

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. It uses specific verbs like 'answers' and explains the resource (edge telemetry from daily snapshots). It differentiates from sibling polymarket_edges by focusing on historical trends rather than current edges.

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

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

The description provides context on when to use the tool, e.g., distinguishing between a fresh wide edge and a 3-week-old edge. It also mentions limits like TTL and snapshot gaps. However, it does not explicitly state when not to use it or offer alternatives among 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, openWorldHint, idempotentHint true and destructiveHint false. The description adds valuable behavioral context: it walks the order book ladder, returns fill details (top_of_book, vwap, slippage, etc.), and for basket mode warns about forced_directional_risk and thin legs. It also explains the risk of partial fills converting arbitrage into unhedged positions. This adds significant transparency beyond annotations, though it does not explicitly restate the read-only nature.

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 fairly long with multiple sentences and two large blocks (SINGLE-MARKET and BASKET). While well-structured with clear section headers, it repeats some information (e.g., modes are described twice). Some sentences are dense and could be split for readability. It is not maximally concise given the complexity, but it is organized logically.

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 compensates by listing all return fields (top_of_book, vwap_fill_price, slippage_pp, etc.) with their meanings. It explains the tool's purpose, when to use it, and failure modes (partial fills, thin books). The 4 parameters are fully covered with defaults and constraints. Given the tool's complexity and risk warnings, the description is 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% for all 4 parameters. The description enhances this by explaining the 'auto' default for side in basket mode, specifying the clamp range for size_usd (10–1,000,000), and clarifying the interpretation of size_usd in single-market vs basket mode. For market and event, it explains the mode they enable. The description adds meaning beyond the schema's property 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 starts with a specific action ('realizable-vs-theoretical edge check against live CLOB order-book depth') and clearly defines two modes (single-market and basket). It differentiates from siblings like polymarket_arbitrage and polymarket_edges by explicitly stating when to use this tool ('USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'). The verb+resource+scope is highly specific and unique among siblings.

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

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

The description provides explicit usage context: it requires either 'market' or 'event', explains the default side and size_usd, and clearly states when to use this tool (before acting on arbitrage signals or large trades). It also explains why it is necessary ('theoretical overround not capturable', 'partial fills convert arb into directional position'), giving both positive and negative usage guidance. The sibling differentiation is strong 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?

With readOnlyHint true and idempotentHint true already covering safety, the description goes well beyond annotations by explaining fees are not modeled, spreads are gross rather than net, compatibility codes can be non-empty even when matched_pairs>0, and unknown legs are never paired. It even warns that temporal_alignment_unknown is not the same as confirmed alignment, which prevents a likely misinterpretation. This is a model of behavioral 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 information-dense and every sentence contributes, but it is exceptionally long and packed into dense paragraphs without bullet formatting or clear visual separation between modes, safety fields, and response semantics. Front-loading is good—the core purpose appears first—but the sheer volume makes it harder for an agent to parse quickly. It could benefit from structured lists or headers.

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

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

There is no output schema, so the description carries full responsibility for explaining return semantics, and it does so thoroughly: leg-by-leg prices, top_spreads_pp, compatibility_warning, compatibility_codes, flags, skipped counters, and fees_note are all explained. The description also covers edge cases such as unclassified legs, temporal alignment uncertainty, and the non-tradeable nature of many pre-mapped topics. Nothing essential to calling the tool correctly 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 baseline is 3, but the description adds significant parameter-level meaning by explaining that 'topic' activates pre-mapped shortcuts while explicit ticker/slug parameters create custom pairings, and that both modes run the identical matcher. It also clarifies that kalshi_event_ticker and polymarket_event_slug override the topic-mapped side, which complements the schema's brief 'Overrides' notes. This moves the score above baseline.

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

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

The description opens by stating the tool computes 'Cross-venue spread between Kalshi and Polymarket for the same resolving question,' naming both the resource and the comparison it performs. It lacks an explicit verb like 'calculate' or 'fetch,' but the meaning is unambiguous. It also implicitly differentiates from sibling tools like polymarket_arbitrage by emphasizing the cross-venue nature, though it does not name a specific sibling.

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

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

The description clearly explains two distinct usage modes: 'topic' shortcuts for pre-mapped events and explicit ticker/slug pairings for custom comparisons, with the schema noting overrides. It also gives practical guidance that pre-mapped topics frequently return compatibility warnings and are not necessarily tradeable. It does not explicitly state when to choose this tool over related siblings like polymarket_arbitrage, but the mode-selection guidance is strong 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 provide readOnlyHint, idempotentHint, destructiveHint. Description adds scoping context and dual behavior (get vs list). It does not contradict annotations. A minor omission is not specifying return format, but overall strong.

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 focused sentences, front-loaded with purpose. No unnecessary words, though the last sentence could be integrated for slight compression.

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 one optional parameter and no output schema, description explains the dual behavior, scoping, and tool relationships. It could mention return value types explicitly, but remains largely complete.

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

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

Schema coverage is 100% with a clear description for 'key'. The description reiterates the omit-to-list behavior already present in the schema, adding no new parameter-level insight beyond what the schema provides.

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

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

Description clearly states verb-resource pair: 'Retrieve a value' or 'list all saved keys'. It distinguishes from siblings 'remember' and 'forget' by specifying it is for retrieval.

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

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

Explicitly states when to use: 'look up context the agent stored earlier... without re-deriving it from scratch.' Mentions scoping by identifier and suggests pairing with 'remember' and 'forget'.

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

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

The description discloses that setting mark_read:true flags events as read, which is a state-modifying action. However, annotations declare readOnlyHint: true, creating a contradiction. The description should either align with annotations or explain the state change.

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

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

The description is a single paragraph of ~80 words, front-loaded with the purpose. It is information-dense but could be more structured with bullet points for parameters. Still within acceptable conciseness.

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

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

The description covers what is returned, filtering options, mark_read behavior, and an alternative access method. It is complete for a list-like tool, but the contradiction with annotations reduces completeness slightly.

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

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

Schema coverage is 100% with descriptions for all 5 parameters. The description adds context like filtering by type (e.g., 'sec_8k') and explains the effect of mark_read, but this largely mirrors the schema. Baseline score 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 'Pull fired events from your subscription feed' and specifies it returns recent alerts with source, citation_uri, and raw event payload. This leaves no ambiguity about the tool's core function.

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

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

The description mentions that polling works fine and provides an alternative URL for scripts/dashboards, offering some usage context. However, it does not explicitly differentiate from sibling tools like list_subscriptions or explain when to prefer this tool.

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

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

The description aligns with annotations (readOnlyHint, idempotentHint, destructiveHint) and adds behavioral traits like fan-out to multiple sources, fallback logic, and soft-fail for patents. 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 a single paragraph that is informative but could be more structured. It is front-loaded with the core purpose, and every sentence adds value.

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

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

Despite no output schema, the description explains the return structure (changes[], total_changes, citation URIs) and covers edge cases like fallback and API sunset. Comprehensive for a read-only feed 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 three parameters have schema descriptions (100% coverage). The description adds extra meaning: 'since' accepts ISO or relative, 'value' can be ticker or CIK, and provides examples. Well above baseline.

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

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

The description clearly states the tool provides a change feed for a company, covering SEC filings, news, and patents, with example queries. It distinguishes from sibling tool entity_profile for static profiles.

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

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

The description includes explicit guidance to use entity_profile for static profiles, explains the fallback behavior for news, and gives hints for the 'since' parameter. It lacks explicit when-not-to-use but provides sufficient context.

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

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

Describes scoping by identifier and retention policies (persistent vs 24-hour). Annotations already show idempotentHint=true and destructiveHint=false; description adds usage boundaries without 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 earning its place. Front-loaded with purpose, followed by usage guidance and pairing tips.

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 without output schema, description covers when, why, scoping, retention, and companion tools. Fully adequate.

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

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

Schema covers both parameters fully. Description adds usage examples but not new param-level details beyond what schema provides.

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

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

Clearly states the tool saves data for reuse across conversations/sessions with specific examples (ticker, address, preference). Distinguishes from sibling tools recall and forget.

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

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

Explicitly tells when to use ('when you discover something worth carrying forward') and how to pair with recall/forget. Provides context for authentication scoping.

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 as read-only, idempotent, and non-destructive, so the description's extra behavioral details add real value. It discloses graceful degradation if GLEIF/OpenFIGI are unavailable, that unresolved identifiers are explicitly listed under `unresolved`, that ambiguous names return `figi_candidates` rather than asserting a wrong answer, and that each call cascades through multiple lookup endpoints. These are exactly the non-obvious behaviors an agent needs to trust results.

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 densely packed and well-structured, front-loaded with example queries and a 'Use FIRST' directive before diving into type details. The parentheticals are extensive but each adds necessary operational nuance; no sentence is purely filler. A slightly tighter organization of the company sub-cases would make it easier to scan, but it is far from bloated.

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 so thoroughly: it names the identifiers returned for each type, labels sources, documents the `unresolved` field, and explains ambiguous-name behavior. It also covers failure/degradation modes. For a tool that internally cascades across multiple lookups, this is complete enough for an agent to call it 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?

Although schema coverage is 100%, the description adds meaning well beyond the schema's terse field text. For `type`, it details what 'company' and 'drug' resolve to, including cross-source CIK/LEI/FIGI vs RxCUI details. For `value`, it provides concrete examples, warns to pass the entity name only, and explains why trailing security-class words cause failures. This materially improves correct invocation.

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

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

The description states a specific verb ('resolve') and resource ('a user-spoken NAME to the canonical/official identifiers other tools require as input'), making the tool's job unmistakable. It also distinguishes the tool's role by noting it is used 'FIRST' when you have a name but need an ID, separating it from downstream tools that consume those IDs. The supported entity types and identifier sources further clarify its scope.

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

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

The description gives explicit invocation guidance: 'Use FIRST whenever you have a name but need an ID.' It also clarifies input formats (ticker, CIK, ISIN, name; brand or generic drug name) and explains edge-case behavior like returning `figi_candidates` when a name is ambiguous. However, it does not explicitly state when not to use this tool or name alternative sibling tools for profile/entity lookups.

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 (false). The description adds value by detailing the internal workflow (probing each entity with ai_visibility_check, ranking by score) and output fields (score, confidence, signal density). This goes beyond annotation-only information.

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, front-loaded paragraph with no extraneous content. Every sentence provides value: main action, internal mechanism, use-case example, and output description. Perfectly concise.

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

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

Given the tool's complexity (multi-entity comparison, internal probes, ranking) and no output schema, the description adequately covers purpose, internal steps, output fields, and constraints (2-8 entities, first is subject). Minor gap: no explicit mention of output ordering direction (ascending/descending), but implied by 'most/least recognized.'

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add significant new meaning beyond what the schema already provides for each parameter (e.g., it restates entity ordering and context purpose). No meaningful enhancement to parameter understanding.

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

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

Description clearly states the tool compares AI visibility across multiple entities, internally uses ai_visibility_check, and returns a ranked list with scores. It distinguishes itself from sibling ai_visibility_check (single entity) and compare_entities (generic 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 explicit use-case context ('competitive AI-marketing audits') with an example question. While it doesn't formally exclude cases, the context is clear enough for an agent to decide when to use this vs. a single-entity tool.

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

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

Adds context beyond annotations: fans out to two services, returns a structured summary, handles partial failures, notes 5-30s delay on bundlephobia first measurement. 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?

Well-structured and front-loaded, but slightly verbose. Every sentence adds value; still clear 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?

Thorough for a complex tool: describes return fields, addresses edge cases (scoped packages, partial failures, timing), and no output schema is compensated by description of output structure.

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. The description adds context about default behavior (version defaults to latest) and scoped packages, but schema already covers parameter meaning.

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

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

The description states it's a composite check for 'should I add this npm package', covering license, advisories, version history, and bundle size. It distinguishes itself from direct deps.dev calls by being a one-call fan-out.

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

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

Explicitly says 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also clarifies scope (NPM only in v1) and handles partial failures gracefully.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds details about embedding model (BGE-base-en), similarity metric (cosine), window size (500-char overlapping), and character cap (200K chars) with truncation/flagging, significantly 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?

The description is thorough yet concise, with each sentence adding value. It front-loads the main purpose and then efficiently explains usage, mechanics, and pairings 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 full schema coverage and the detailed behavioral disclosure, the description is complete. It addresses return values (passages with offsets and scores) despite no output schema, making it fully informative for an AI agent.

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

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

Schema coverage is 100% with adequate descriptions. The description adds extra meaning by specifying the character cap for 'text' and providing example queries for 'query', going beyond what the schema alone offers.

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 ('Semantic search INSIDE a fetched record') and clearly identifies the resource (a source/record). It distinguishes from siblings by referencing ask_pipeworx_grounded and the context of large records.

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 when the record is too big to cram into the prompt.' Also describes benefits (saves context, returns relevant passages with offsets) and pairs with another tool.

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

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

Annotations already indicate non-readOnly and non-destructive behavior with idempotentHint=true. The description adds essential behavioral context like authentication requirements, delivery channel constraints (email/SMS verification, 10/day cap), and that webhook secret is returned once. It does not clarify if multiple identical subscriptions are allowed or return the same ID.

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 the main action first, followed by prerequisites, types, and delivery details. It is relatively long but every sentence adds value; minor improvement could be grouping some constraints more concisely.

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

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

Given no output schema and three parameters including nested objects, the description covers all key aspects: authentication, types with required and optional params, delivery channels, and return value (subscription id). It could mention if the feed is always-on or confirm the exact return object structure.

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, but the description adds significant value by providing concrete examples for each subscription type (e.g., items codes for sec_8k, min_spread_bps for polymarket_edge) and detailed delivery channel options including webhook signing and auto-disable conditions.

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

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

The description clearly states the action ('Create a proactive monitoring subscription'), resource ('live-data event stream'), and lists specific subscription types, distinguishing it from sibling tools like list_subscriptions or 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?

It specifies the requirement for a Pipeworx OAuth account and says anonymous/BYO users cannot persist subscriptions, providing clear context. However, it does not explicitly mention when not to use this tool or suggest alternatives like polling.

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. The description adds context about return content (categories with tool shapes) and parameter effect, but no additional behavioral disclosures beyond that.

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

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

The description is relatively long but well-front-loaded with example queries. It is structured and each sentence adds value, though slight verbosity prevents a perfect score.

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

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

Given no output schema, the description covers what the tool returns, how to invoke it, and when to use it. With annotations, it is largely complete for a discovery tool.

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

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

Schema coverage is 100% and already describes the topic parameter. The description adds value by clarifying omission gives full spread and providing concrete topic 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 returns category-bucketed example questions with exact tool+argument shapes. It is an onboarding entry point, distinct from siblings that perform other tasks.

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

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

Explicitly states 'Use this FIRST when you do not yet know what Pipeworx can do for you' and explains when to omit args vs. pass a topic.

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

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

Beyond annotations (idempotent, non-destructive, readOnlyHint false), the description adds critical behavioral details: ownership enforcement and soft-delete semantics. No contradiction with annotations.

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

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

Two succinct sentences with no redundancies. The key action and constraints are front-loaded, making it highly 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?

For a simple one-parameter tool with annotations, the description fully covers purpose, ownership, and post-action state. No output schema, but not needed given the context.

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

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

Schema coverage is 100% and the single parameter 'id' is fully described in the schema. The description does not add additional parameter-specific meaning beyond what the schema provides.

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

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

The description clearly states the action ('Cancel a subscription by id') and immediately specifies the resource and ownership constraint. Distinguishes well from sibling 'subscribe' by being its inverse.

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 (own subscriptions) and what happens (deactivation, not deletion). Though no alternative tools are mentioned, the context is clear 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?

Annotations already declare readOnly/idempotent/openWorld, and the description adds high-value semantics: the exact verdict vocabulary, the critical disambiguation between could_not_verify and unsupported, and the presence of verification_error. This prevents misuse where a failed check might be mistaken for refutation.

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 packs substantial behavioral guidance into a structured, front-loaded format without fluff. Each clause about the two pipelines, verdict meanings, and caller warning adds necessary operational detail, so length is justified.

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 enumerates all possible verdicts and explains ambiguous ones, along with the returned value and citation. It also clarifies the tool's place among siblings by describing its scope, making it self-sufficient for an agent to invoke correctly.

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

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

Both parameters are fully described in the schema (100% coverage), so the description doesn't need to restate them. It adds context about tolerance via 'exact percent-delta math' and the claim examples, but effectively relies on the schema for param specifics — baseline 3.

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

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

Clearly identifies the tool as a claim-verification service with explicit natural-language triggers ('fact check', 'verify the claim that...') and states it returns verdicts. It differentiates from sibling research tools by focusing on true/false adjudication against authoritative sources rather than general Q&A or deep research.

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

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

Explicitly instructs 'Use whenever the agent needs to check whether something a user said is factually correct' and details the two routing paths (structured SEC for company-financial claims, grounded pipeline for all others). It notes this tool replaces 4–6 sequential calls, implying it is the consolidated path versus manual staging, though it doesn't name specific sibling alternatives.

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