Harvard Art

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds: default model behavior, API key handling for Anthropic (passed directly), and return structure (per-model fields + combined view). No contradictions.

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

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

The description is well-structured with two clear parts: functionality and usage guidance. It is efficient but slightly wordy in places; however, 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 4 parameters, no output schema, and no nested objects, the description covers the core behavior, model options, return format, and use cases. It is adequately complete for an agent to understand and invoke the tool.

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

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

Schema coverage is 100% with descriptions for all 4 parameters. The description reinforces parameter meanings (e.g., '_apiKey' is used for Anthropic) and adds context about defaults and return format, providing value beyond the schema.

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

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

The description uses specific verb 'Probe' and identifies the resource as LLMs about an entity, with clear output (visibility score 0-100 per model). It distinguishes from siblings like 'scan_competitor_ai_presence' by focusing on scoring visibility rather than scanning presence.

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

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

The description lists use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and mentions model selection (default free, Anthropic with key). It does not explicitly state when not to use, but the context is clear. Could be stronger with direct comparisons to alternatives like 'ask_pipeworx'.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds context: routes questions to one of 4482 tools, returns structured answer with stable citation URIs, and is a fast single call. 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 verbose but well-structured: it front-loads the priority message, uses examples, and each sentence adds value. Some redundancy could be trimmed but overall effective.

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

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

Given no output schema, the description adequately explains the return (structured answer with citations). It covers routing, use cases, and integration with other tools. The tool is simple (one effective parameter) and the description 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 has 100% coverage for the question parameter and its aliases. The description does not add additional parameter details beyond what the schema already provides. Baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: answering factual questions with authoritative structured data from many sources. It explicitly prefers this tool over web search and distinguishes from siblings 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?

The description provides explicit when-to-use scenarios (e.g., 'what is', 'look up', factual questions) and when-not (hallucination-resistant, broad multi-part). It also names specific alternatives and advises 'START HERE for most questions'.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and no destructiveness. The description adds valuable behavioral context: it costs one extra LLM call, extracts answers only from tool results, and returns explicit refusal reasons. 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 front-loaded with purpose and key distinction, followed by return format and usage guidelines. It is informative but slightly lengthy; however, every sentence adds value. Could be slightly trimmed but overall well-structured.

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

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

Despite having no output schema, the description fully details the return structure (answer, evidence, confidence, source, refusal_reason) and all possible refusal reasons. It explains the routing to 4,482 tools and extraction logic, providing complete context for agent usage.

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

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

Schema coverage is 100% with descriptions for all 6 parameters (aliases for question). The description doesn't add parameter-level meaning beyond stating it accepts natural language questions. Baseline 3 is appropriate as schema already documents parameters.

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

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

The description explicitly states it's a 'Hallucination-resistant answer mode for high-stakes reads' and clearly distinguishes from sibling 'ask_pipeworx' by highlighting the extra extraction step and refusal behavior. The verb 'answer' with 'grounded' modifier and specific use cases make the purpose clear.

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

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

The description provides explicit when-to-use (high-stakes reads where answers will be quoted/cited/acted on) and when-not-to-use (casual lookups, prefer ask_pipeworx). It lists concrete examples like financial verdicts, legal claims, medical lookups, promoting correct tool selection.

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

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

The description extensively details behavioral traits beyond annotations, including fan-out examples, response shapes, safety short-circuits, edge cases like closed markets, wide spreads, and resolution-rule risk. 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 lengthy but well-structured with section headers (CLASSIFIERS, FAN-OUT, etc.) and front-loads the core purpose. Every sentence adds value, though some details could be streamlined.

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 (no output schema but described in detail), the description covers input, processing logic, output shapes, edge cases, and safety mechanisms thoroughly.

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

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

All three parameters are described in the schema with full coverage. The description adds examples, default behavior, and explanation of parameter effect (e.g., include_raw keeps responses small).

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 researches a Polymarket bet using Pipeworx data in one call. It specifies the verb (research) and resource (Polymarket bet via Pipeworx), and distinguishes itself from siblings by being a focused bet research tool, not a general search or validation tool.

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

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

The description provides explicit use cases ('Use for "should I bet on X"...') and hints at when not to use (e.g., low-confidence matches). It lacks explicit alternatives but covers context well.

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, so the description carries a lighter burden. It adds value by explaining data source specifics (SEC EDGAR/XBRL for companies, FAERS for drugs) and behavior like off-calendar fiscal year handling and result sorting by primary metric. No contradictions with annotations.

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

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

The description is moderately long but every sentence serves a purpose: it lists query patterns, explains functionality, data sources, and usage preference. It could be slightly tighter (e.g., removing repeated phrases), but it remains well-structured and front-loaded with key behavior.

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 only 2 parameters, 100% schema coverage, and thorough annotations, the description covers all necessary context: data sources, constraints (2-5 items), sorting, citation URIs, and performance benefit over sequential lookups. No output schema exists, but the description provides sufficient understanding of return value 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?

With 100% schema coverage, the description goes beyond by explaining what each type (company vs drug) means in terms of data pulled and gives formatting examples for values (tickers for company, names for drug). This adds significant meaning beyond the schema's enum and array 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 clear query patterns ("Compare X and Y", "X vs Y") and explicitly states the tool performs "side-by-side comparison of 2–5 companies or drugs in ONE parallel call." It distinguishes from sequential lookups and specifies data sources for each entity type, making the purpose unmistakable.

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

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

The description explicitly instructs to "ALWAYS PREFER over sequential single-pack lookups when comparing entities," providing clear usage context. It also gives example queries and conditions for when to use (e.g., comparing financials or drug metrics), effectively guiding the AI agent on when to invoke this tool over siblings.

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

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

Adds significant behavioral context beyond annotations: account requirement, paid plan for 'thorough', parallel execution, expected response time, and the gaps[] array for unanswered facets. No contradiction with annotations.

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

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

Description is well-structured with clear sections and uses bold for emphasis, but is slightly lengthy. However, every sentence serves a purpose, and the structure aids readability.

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

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

Given the tool's complexity and many siblings, the description covers purpose, usage, parameters, and limitations. Despite no output schema, it explains the return format (findings packet with evidence, source, confidence, etc.), providing sufficient completeness.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining the depth enum values (quick=3 facets, standard=5, thorough=8) and emphasizing that the question should be broad/multi-part, enhancing understanding beyond schema.

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

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

Description clearly states it performs grounded multi-source research across structured data sources, decomposing questions into facets and returning evidence packets. It distinguishes itself from sibling tools like ask_pipeworx (single lookup) and highlights its scope (structured data, not open-web search).

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 this tool (broad/multi-part over structured data) and when not to (breaking news, colloquial current news), providing alternatives like ask_pipeworx. Also mentions account and plan requirements.

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

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

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already indicate safe, read-only behavior. The description adds value by detailing what is returned: '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.' This goes beyond annotations without contradicting them.

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 primary purpose and usage instruction. It lists many examples but they are relevant and aid comprehension. Each sentence adds meaningful information, though the list of domains could be trimmed without loss of clarity. Still, it remains efficient for the information conveyed.

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

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

The description explains the output format (names, descriptions, schemas) and that results are ready to call, which is sufficient given no output schema. It doesn't mention relevance ranking or pagination, but for a discovery tool expecting zero or few results, this is adequate. The level of detail matches the tool's simple purpose.

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

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

Schema coverage is 100% (all 6 parameters described), so baseline is 3. The description adds value by listing aliases for query (task, q, description, search) and providing concrete examples for query values ('analyze housing market trends', 'look up FDA drug approvals'). This reduces ambiguity and helps the agent form effective queries.

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 'Find tools by describing the data or task,' clearly identifying the verb (find/discover) and resource (tools). It distinguishes from siblings like 'search' and 'deep_research' by emphasizing browsing/discovering available tools rather than executing a specific search. The list of domains (SEC filings, FDA drugs, etc.) further clarifies scope.

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

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

Explicitly states 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This gives a clear when-to-use instruction and implies a sequencing priority. It also lists example tasks, helping the agent determine applicability.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable context: it fans out across multiple sources, returns specific data, notes patents API sunset and soft-fail behavior, and that names are not supported. No contradictions with annotations.

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

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

The description is a single dense paragraph that front-loads example queries and key benefits. It includes all necessary information without being overly verbose, though a bit more structure (e.g., bullet points) could improve readability.

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

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

Given no output schema, the description explains the return values in detail (CIK, filings with URIs, fundamentals sorted, patents, news fallback, LEI). It also mentions potential issues (patents API sunset), providing complete context for the agent.

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

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

Schema coverage is 100%, and the description adds meaning beyond the schema: type is only 'company', value must be ticker or zero-padded CIK, names not supported. This helps the agent understand the constraints and usage.

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

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

The description clearly states the tool's purpose: 'full cross-source profile of a US public company in ONE parallel call.' It lists example queries and explains what it returns (CIK, filings, fundamentals, patents, news, LEI). It distinguishes from siblings like resolve_entity and compare_entities.

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

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

The description explicitly says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also advises using resolve_entity first if only a name is available. However, it doesn't explicitly state when not 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 already indicate destructiveHint=true and readOnlyHint=false. The description adds context about clearing sensitive data, which is helpful but not critical beyond the annotations.

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

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

Three sentences, all relevant and front-loaded with the core action. No superfluous information.

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

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

Given the simplicity of the tool (one parameter, no output schema), the description provides complete context: purpose, when to use, and related tools.

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 the single parameter 'key'. The tool description does not add any additional meaning beyond what the schema already provides.

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

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

The description clearly states 'Delete a previously stored memory by key', using a specific verb and resource. It distinguishes from siblings by specifying deletion as opposed to remembering or recalling.

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 use cases: 'when context is stale, the task is done, or you want to clear sensitive data'. Also mentions pairing with siblings 'remember and recall', giving clear guidance.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds value by explaining it fetches the page, extracts info, and emits standard format. 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 three sentences, front-loading the main action. Every sentence serves a purpose, no fluff.

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

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

Given 2 parameters, no output schema, and rich annotations, the description is complete: it explains output format (single text blob for site-root/llms.txt) and use cases, leaving 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 description coverage is 100%, so baseline is 3. The description adds minimal beyond schema (e.g., example URL), not significantly enriching 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 clearly states the tool generates a production-ready llms.txt file for any URL, specifying the verb 'generate', the resource 'llms.txt file', and the context 'for any URL'. It distinguishes from siblings like scan_competitor_ai_presence by focusing on file generation.

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

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

The description provides explicit use cases: getting a client's site indexed by AI, drafting for own project, or auditing competitor's AI crawl view. While it doesn't give negative guidance, the positive use cases 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: true and idempotentHint: true. Description adds context about active-only default and return fields, but no extra 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, front-loaded with purpose, no unnecessary words.

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

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

For a simple listing tool with one optional param and good annotations, description fully covers return fields and usage context.

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

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

Only one parameter with 100% schema description coverage. Description does not add new info beyond the schema's description.

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

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

Clearly states 'List the caller's active subscriptions' and specifies return fields. Differentiates from sibling tools like subscribe and unsubscribe.

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

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

Explicitly advises using this tool to review monitored subscriptions before adding more or to find an id to cancel, providing clear when-to-use guidance.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds minimal behavioral context ('Fetch full details'), which is already implied by annotations. No contradictions.

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

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

Single sentence, front-loaded with purpose and constraint. No extraneous words. Every word 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 simple tool with rich annotations and complete schema, description is adequate. No output schema, but 'full details' implies comprehensive return. Could mention expected response structure, but not necessary for clarity.

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

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

Schema coverage is 100% with descriptions for both parameters. Description adds no additional semantics beyond schema (e.g., 'e.g. "299843".'). Baseline score of 3 is appropriate.

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

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

Description clearly states verb ('Fetch'), resource ('full details for one Harvard Art Museums item'), and input constraint ('by id — a Harvard Art Museums object id (numeric, from search)'). It distinguishes from sibling tools like 'search' or 'entity_profile' by specifying a unique operation on a specific API.

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

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

Description implies use when a numeric object id is available ('by id — a Harvard Art Museums object id (numeric, from search)'), but does not explicitly state when not to use or provide alternatives. No exclusions or comparisons with 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 are all false, so no inherent behavioral hints. The description adds critical behavioral context: rate-limited to 5 per identifier per day, free, and doesn't count against tool-call quota. 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 four sentences long, front-loaded with the action, then usage guidelines, then behavioral notes. Every sentence adds value and there is no redundancy.

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

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

Given the simple tool (3 params, no output schema), the description covers purpose, usage scenarios, constraints (rate limit, cost), and proper formulation of feedback. It is fully adequate for an agent to decide when and how 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% with each parameter well-described. The description does not add new semantic details beyond the schema, so it meets the baseline of 3.

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

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

The description clearly states the tool's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It uses a specific verb-resource combination and distinguishes itself from sibling tools (e.g., search, research) by being the only feedback submission tool.

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

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

Explicitly describes when to use: for bug, feature, data_gap, or praise. Also gives a clear 'when-not' instruction: 'don't paste the end-user's prompt.' Provides context about team responsiveness and roadmap impact.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds valuable context: data source (CF analytics-engine), no PII, caching behavior (5min-1h), and aggregation details.

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

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

Three sentences with bullet-like numbered uses. Front-loaded with main output. No redundant information; 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, description fully explains return values (top tools, packs, volume). Also covers caching, derivation, and privacy. Complete for a read-only trend tool.

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

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

Schema coverage is 100% with enum descriptions. Description adds nuance: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' Exceeds 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?

Description specifies verb 'returns' and resource 'top tools, top packs, and total call volume' with time windows. Clearly distinguishes from sibling tools like 'discover_tools' by focusing on trending 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?

Lists three explicit use cases (discovering hot sources, confirming canonical tools, aligning use cases). Lacks explicit when-not-to-use instructions, but context is clear given 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?

The description goes beyond annotations (readOnly, idempotent, non-destructive) to detail internal algorithms (monotonicity checks, partition-sum, Jaccard similarity), edge cases (empty args fail, low similarity skipped, placeholder filtering), and the fill check against live CLOB depth.

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

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

The description is lengthy but well-structured with clear sections (requirements, modes, algorithms, response fields). It could be slightly more concise, but every section adds necessary detail for correct usage.

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

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

Given the tool's complexity (two modes, multiple algorithms, fill check integration), the description covers input constraints, internal logic, edge cases, response structure, and links to related tools. It is comprehensive for an agent to use 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%, but the description adds significant value: it explains the difference between event and topic, provides usage recommendations, gives examples of valid inputs, and describes failure behavior when called with no arguments or inappropriate values.

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

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

The description clearly states the tool's purpose: finding arbitrage opportunities on Polymarket using monotonicity violations and partition-sum checks. It distinguishes between event and topic modes, and contrasts with sibling tools like polymarket_fill_risk.

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 requires one of `event` or `topic`, and explains when to use each mode. Recommends event for specific markets and topic for cross-event scanning. Also provides guidance on when not to trade (realizable_edge_pp ≤ 0) and mentions sibling tools for custom sizing.

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 is exceptionally detailed, explaining the three model families with methodology, the exclusion of fed_candidates due to data unreliability, caching at KV level keyed on knobs, and the output structure including diagnostics. All behavioral traits disclosed go far beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint). No contradictions.

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

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

The description is comprehensive but verbosely detailed. It front-loads the purpose and then dives into technical specifics of each model family. While every sentence adds value, the length could be slightly trimmed for conciseness. However, given the complexity of the tool, the detail 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?

The description fully compensates for the lack of an output schema by exhaustively listing all response fields (by_segment, fed_candidates, _diagnostics) and explaining each segment's content. It covers all nine parameters indirectly through context and provides ample guidance on interpretation. No gaps remain.

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

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

Schema coverage is 100% with detailed parameter descriptions. The description does not add new information about individual parameters beyond what the schema provides, but it reinforces the purpose of the tradeable-edge knobs (min_liquidity, max_spread_pp, min_partition_leg_kelly) in context. Baseline 3 is appropriate.

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

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

The description clearly states the tool scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It defines three specific segments (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) and distinguishes itself from siblings like polymarket_arbitrage by focusing on model-driven edge discovery.

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

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

The description explicitly says it's built for 'what should I bet on today' and helps agents discover opportunities without paging hundreds of markets. It explains tradeable-edge knobs (min_liquidity, max_spread_pp) that filter when an edge is not realizable. However, it does not explicitly contrast with sibling tools or state when not to use it.

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

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

The description adds significant behavioral details beyond the annotations (readOnlyHint, openWorldHint, etc.), such as the 60-day snapshot TTL, snapshot gaps, non-intraday decay numbers, and the nature of data sources. No contradictions with annotations.

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

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

The description is thorough but slightly lengthy. However, it is well-structured with a clear lead sentence, detailed response breakdown, and limitations. Each part earns its place, but some redundancy could be trimmed.

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

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

Given no output schema, the description fully explicates the response fields (tracked, expired, snapshot_dates) with subfields and meanings. It also covers parameters, behavioral constraints, and edge cases (gaps, TTL). Very complete.

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

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

Schema description coverage is 100%, but the description adds extra context: default values, clamping range, and detailed explanation of the response structure. This compensates for the lack of an output schema and adds meaning beyond the schema.

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

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

The description clearly states the tool's purpose: providing edge persistence and decay telemetry from daily snapshots. It answers a specific question ('how long has this edge existed and is it shrinking?') and distinguishes itself from sibling tools like polymarket_edges by focusing on historical tracking.

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 implicitly guides usage by contrasting fresh vs. old edges and explaining what the tool answers. It lacks explicit when-to-use or when-not-to-use guidance compared to siblings, but the context is clear enough for most cases.

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

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

Annotations already indicate readOnly, idempotent, non-destructive behavior. The description adds significant behavioral detail: walking the order book ladder, returning specific fields (top_of_book, vwap_fill_price, slippage_pp, verdict), and explaining risk of thin books and unhedged positions. 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 front-loaded with the main purpose but is somewhat lengthy (approx. 200 words). However, it is well-structured with all-caps headings for key sections (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) and every sentence adds value, justifying the length for a complex tool.

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

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

Despite no output schema, the description thoroughly explains return values for both modes, including specific fields like top_of_book, verdict, thin_legs, and forced_directional_risk. It also gives enough context for the tool's complex behavior, making it self-contained.

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

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

Schema description coverage is 100%, and the description adds meaning beyond the schema by explaining defaults (size_usd=1000, side auto for basket), ranges (clamp 10–1,000,000), and mode-specific interpretation of parameters like size_usd as settlement notional in basket mode.

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 as a 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes between single-market and basket modes and explicitly differentiates from sibling tools like polymarket_arbitrage and polymarket_edges by advising when to use it.

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

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

The description provides explicit guidance on when to use the tool: before acting on polymarket_arbitrage signals or polymarket_edges trades above ~$500. It warns about risks of partial basket fills converting arb into directional positions, offering clear usage context.

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

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior. The description adds extensive behavioral context: how spreads are computed (Kalshi − Polymarket), the structure of the response, safety fields (compatibility_warning, temporal_alignment, skipped counters), and explanations for why spreads may not exist (bet shape mismatches, temporal gaps). 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 lengthy but well-structured with clear sections for modes, response, safety fields, and a concluding note. Every sentence adds value, though a minor reduction in verbosity (e.g., combining repeated warnings) could improve conciseness without losing information.

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

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

With no output schema, the description thoroughly explains return values: leg-by-leg prices, matched spread top_spreads_pp, compatibility_warning, temporal_alignment, skipped_cross_type/subtype counters. It also describes how to interpret these fields and addresses edge cases, making the tool fully self-contained 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%, but the description adds significant meaning: it explains the two modes, lists the topic shortcut values, provides example tickers (KXFED-26OCT, fed-decision-in-june-825), and clarifies that explicit parameters override the topic mapping. This goes well beyond the schema's bare 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 computing cross-venue spreads between Kalshi and Polymarket. It specifies two modes (topic shortcuts and explicit tickers) and distinguishes itself from siblings like polymarket_arbitrage by focusing on cross-venue analysis.

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 the list of pre-mapped topics and how to override them with explicit parameters. It warns that most pre-mapped topics currently return compatibility warnings and that pre-mapped does not imply tradeability, helping agents avoid misuse.

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, non-destructive, idempotent. Description adds value by explaining scoping (anonymous IP, BYO key hash, account ID) and behavior on omitted key. 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?

Three clear, front-loaded sentences with no redundancy. First sentence defines core action, second gives examples, third adds scoping and pairing. 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?

With one parameter, strong annotations, and no output schema, the description fully covers purpose, usage, behavioral notes, and relationships to siblings. 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 covers 100% of parameter with description. Description adds meaning: omitting key lists all keys, and references sibling tools for save/delete. Provides practical usage context.

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

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

Description clearly states it retrieves saved values or lists keys, uses specific verb 'retrieve', and distinguishes from siblings 'remember' and 'forget'.

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

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

Explicit when-to-use context (look up stored data like ticker, address, notes) and hints at alternatives (pair with remember/forget). Lacks explicit when-not-to-use but context is clear.

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

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

Annotations indicate readOnly, openWorld, idempotent, non-destructive. The description adds key behavior: mark_read flag to update read state and that polling works fine. No contradictions.

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

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

The description is concise with 5 sentences, front-loaded with the main purpose. Every sentence adds value without redundancy.

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

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

Given no output schema, the description explains return fields (source, citation_uri, payload) and covers all parameters and behavioral notes. It is complete for an agent to 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 covers all 5 parameters (100% coverage). Description adds examples (e.g., 'sec_8k' for type) and clarifies mark_read effect, but does not add significant new semantics 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 pulls fired events from a subscription feed, specifying the returned fields and available filters. It distinguishes from siblings like list_subscriptions and subscribe by focusing on event retrieval.

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

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

The description explains when to use the tool (to get recent alerts) and mentions an alternative HTTP endpoint for scripts/dashboards. However, it does not explicitly state when not to use it or compare with other tools like search.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds behavioral context: fans out to multiple sources, fallback logic, soft-fail for USPTO, and return structure (changes grouped by source + total_changes + citation URIs). No contradiction.

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

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

Description is moderately sized, front-loaded with usage examples and then technical details. Every sentence adds value. Slightly verbose but still efficient.

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

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

Given the complexity (multiple sources, fallback, soft-fail, no output schema), the description is complete. It covers input semantics, source behavior, and when to use the sibling 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 meaning beyond schema: explains 'since' accepts ISO date or relative shorthand with examples, 'value' can be ticker or CIK, and 'type' is only 'company'. Well-explained but could further detail output structure.

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

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

Description clearly states the tool retrieves a change feed (SEC filings, news, patents) for a company in a time window. It distinguishes from sibling tool 'entity_profile' which provides static profile.

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

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

Provides explicit when-to-use scenarios ("What's new with X") and directs to use 'entity_profile' for static profile. Also explains fallback behavior (GDELT preferred, GNews on failure) and soft-fail for USPTO.

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 behavioral traits beyond annotations: key-value pairing, scoping by identifier, persistence differences for authenticated vs. anonymous users, and 24-hour retention for anonymous sessions. It also mentions integration with recall and forget. No contradiction with annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false).

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

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

The description is concise and front-loaded: first sentence states the primary purpose, followed by usage guidance and behavioral details. Every sentence adds value without redundancy. Efficient structure for an AI agent.

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

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

Given the annotations (idempotentHint=true) and schema, the description covers all needed context: storage mechanism, persistence, lifecycle, and integration with siblings. No output schema is required for a write operation. Complete and self-sufficient.

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

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

Schema coverage is 100%, so the schema already documents both parameters. The description adds example key patterns (e.g., 'subject_property', 'target_ticker') and explains the value is 'any text', adding context beyond the schema. Baseline 3, plus 1 for semantic enrichment.

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

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

The description explicitly states the tool's purpose: 'Save data the agent will need to reuse later.' It specifies the action (save), resource (data/key-value pair), and scope (across sessions, scoped by identifier). It distinguishes from sibling tools recall and forget, providing clear differentiation.

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

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

The description provides clear guidance on when to use: 'when you discover something worth carrying forward' and pairs with recall and forget. It contextualizes based on authentication state (persistent vs. 24-hour retention). However, it does not explicitly state when not to use the 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 read-only, open-world, idempotent, and non-destructive hints. The description adds significant behavioral context: it cascades through multiple endpoints internally, auto-disambiguates for companies, and specifies the exact return structure for each type (ticker, CIK, citation URI for company; RxCUI, ingredient, brand for drug). 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 moderately long but well-organized: it starts with usage examples, then states the core purpose, and breaks down supported types with return values. Every sentence adds value; there is no fluff. It could be slightly more concise, but the structure is clear.

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

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

Given the tool's simplicity (2 parameters, no output schema), the description is comprehensive. It covers input (what values to provide), output (what is returned), and internal behavior (cascading lookups). There are no missing aspects that would leave an agent uncertain.

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

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

Schema coverage is 100%, but the description adds rich meaning beyond the schema. For the 'type' parameter, it clarifies the two options with examples. For 'value', it provides multiple input formats (ticker, CIK, name for company; brand or generic for drug) and explains that the tool auto-disambiguates. This greatly aids agents in parameter selection.

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

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

The description clearly states the tool resolves a user-spoken name to a canonical identifier, with specific verb+resource ('resolve an entity'). It provides example queries ('What's the ticker for...') and lists supported types (company, drug). It implicitly distinguishes from sibling tools by emphasizing it is the first go-to for name-to-ID resolution.

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

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

The description explicitly says 'Use FIRST whenever you have a name but need an ID.' This gives clear context on when to use the tool. It also mentions that it replaces 2-3 manual lookups. However, it does not explicitly state when not to use it or name alternative tools for different scenarios, which would elevate the score.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral context: it probes each entity with ai_visibility_check, ranks results, and returns scores/confidence/signal density. It also notes the optional Anthropic API key, which is a behavioral detail. No contradictions with annotations.

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

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

The description is extremely concise: two sentences plus a brief parenthetical example. Every sentence adds value, and it is front-loaded with the main action and purpose.

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

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

Given four parameters and no output schema, the description adequately covers inputs and outputs (ranked list with score, confidence, signal density). It does not explain signal density or confidence in detail, but references ai_visibility_check, which likely provides more info. The description is sufficient for the tool's complexity.

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

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

Schema coverage is 100%, but the description adds meaning beyond the schema by explaining that entities should be 2-8, first is the subject, context disambiguates, and _apiKey is needed only for anthropic. This enriches the agent's understanding.

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

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

The description clearly states that the tool compares AI visibility across multiple entities, uses ai_visibility_check, ranks by score, and identifies most/least recognized. It distinguishes itself from sibling tools like ai_visibility_check (single entity) and compare_entities (general comparison).

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

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

The description provides a clear use case ('competitive AI-marketing audits') and an example question, giving the agent sufficient context for when to use the tool. However, it does not explicitly mention when not to use it or contrast with alternatives like compare_entities.

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

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

Beyond annotations (readOnly, idempotent, openWorld, non-destructive), description adds key behaviors: partial failures, 5-30s delay for new versions, graceful degradation with sources_failed field. 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?

Single paragraph is dense but clear, front-loaded with core purpose. Could be slightly more structured (bullet points) 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?

No output schema, yet description lists all return fields (summary block, advisory detail, links, alternative versions) and covers partial failure. Handles 2 params fully, ecosystem scope clear.

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

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

Schema coverage is 100%. Description adds value by noting scoped packages accepted for 'package' and default behavior for 'version', but does not fundamentally extend beyond schema.

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

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

Description clearly states it's a composite check for npm packages covering safety, popularity, size, and provides specific example (lodash). Distinguishes from siblings by noting NPM-only in v1 and other ecosystems via deps.dev.

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...' and lists example queries. Also specifies when not to use (other ecosystems) and gives alternative (deps.dev:version). Also mentions partial failure handling.

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

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds that items include ids, titles, creators, dates, and image links, and hints at using returned ids with the 'object' tool. This provides minimal extra value beyond the annotations.

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

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

The description is two sentences with clear front-loading of the action and resource. Every word adds value, with no fluff or repetition.

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

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

Given the tool's simplicity (keyword search, 4 parameters, rich annotations), the description covers the essential purpose and output fields. It lacks pagination behavior details or error conditions, but these are partially covered by annotations and schema. For a straightforward tool, it is fairly complete.

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

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

Schema description coverage is 100%, so each parameter is documented. The description does not add new parameter-specific information beyond what is in the schema, meeting the baseline for complete schema coverage.

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

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

The description specifies the verb 'search', the resource 'Harvard Art Museums collection', and the keyword method. It distinguishes from siblings like 'search_within' by being a general keyword search, and clearly states the returned fields.

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

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

The description implies usage for keyword-based searches but offers no explicit guidance on when to use this tool over siblings like 'search_within' or 'object', nor any when-not-to-use conditions. Context is adequate but not directive.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds detailed behavioral information: BGE-base-en embeddings, cosine similarity over 500-char overlapping windows, character offsets, and a 200K character cap with truncation flagging. This goes well beyond annotations without contradiction.

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

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

The description is a single dense paragraph, front-loaded with the core purpose. It packs significant information concisely, though it could benefit from slightly more structured formatting (e.g., bullet points) for easier scanning.

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

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

Despite having no output schema, the description sufficiently explains what the tool returns: top-N passages with character offsets and similarity scores. It also covers truncation and embedding details, making it complete for an AI agent to understand and 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 parameters are already documented. The description adds value by providing concrete examples for the query parameter and clarifying the text length limit. This enhances understanding beyond the schema alone.

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

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

The description clearly states the tool performs semantic search inside a previously fetched record, distinguishing it from general search tools. It uses specific language like 'search_within saves context' and pairs with ask_pipeworx_grounded, making its purpose unambiguous.

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

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

The description explicitly says to use this tool when the record is too large for the prompt, and it mentions pairing with ask_pipeworx_grounded. While it gives clear context, it does not explicitly state when not to use it, which prevents a perfect score.

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

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

Beyond annotations, the description discloses authentication requirements, type-specific filters, delivery constraints (phone verification, SMS cap), webhook auto-disable, and signing. This fully informs the agent of tool behavior.

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

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

The description is dense but well-structured, starting with the main purpose, then requirements, types, and delivery. It could benefit from bullet points for readability, but it remains concise and front-loaded.

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

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

Given the complexity of multiple subscription types and delivery channels, the description covers authentication, rate limits, webhook behavior, and return value. No gaps identified; the agent has sufficient information to use the tool correctly.

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

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

The input schema covers 100% of parameters, but the description adds rich examples for each type and explains delivery channel intricacies, such as webhook signing and SMS validation, enhancing meaning 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 creates a proactive monitoring subscription. It distinguishes itself from siblings like 'unsubscribe' and 'list_subscriptions' by detailing subscription types and delivery channels.

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 this tool (proactive monitoring) and includes prerequisites (OAuth account). However, it does not explicitly contrast with alternatives like one-time queries, leaving some ambiguity.

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

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

Annotations already declare readOnlyHint, idempotentHint, and no destructiveness. Description adds meaningful behavioral context: it returns examples with tool shapes and is a read-only discovery tool, consistent with annotations.

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

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

Description is slightly long but well-structured with front-loaded user intents and no wasted words. Every sentence contributes useful information.

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

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

Given no output schema, description adequately explains what is returned (category-bucketed examples with tool+argument shapes). Sufficient for a simple 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 covers all parameters (100% description coverage), but description enriches the one parameter 'topic' with concrete examples and the default behavior ('omit for a cross-category spread'), going 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 uses specific verbs and resources ('returns category-bucketed example questions', 'onboarding entry point') and clearly distinguishes from siblings like ask_pipeworx by framing it as the first step for new users.

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

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

Explicitly says to use this 'FIRST when you do not yet know what Pipeworx can do' or 'to learn how to call the meta-tools', providing clear context. Could add explicit when-not-to-use, but the guidance is strong.

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

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

Annotations already indicate idempotent and non-destructive. Description adds critical context: deactivation (not deletion), historical events preserved via recent_alerts, and ownership enforcement.

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, no filler, front-loaded with action. Every sentence adds value.

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

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

For a single-parameter tool with no output schema, the description covers purpose, behavior, side effects, and relationship to sibling tool 'recent_alerts'. Complete given 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?

Single parameter 'id' is fully described in schema (100% coverage). Description adds 'by id' but no extra semantic meaning beyond schema.

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

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

Clearly states the verb 'Cancel' and the resource 'subscription by id'. Ownership enforcement and soft-deactivation distinguish it from siblings like 'subscribe' and 'list_subscriptions'.

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

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

Specifies ownership enforcement ('you can only cancel your own subscriptions') and outcome ('deactivated, not deleted'). Does not explicitly state when-not-to-use or list alternatives, but context is adequate.

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

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

The description adds significant behavioral context beyond annotations, detailing return values (verdict, structured form, actual value, citation, percent delta), data sources (SEC EDGAR + XBRL), and efficiency gains (replaces 4-6 calls). Annotations already indicate safe, idempotent, open-world nature; description enriches with operational details.

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

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

The description is relatively long but well-structured, starting with example queries to immediately convey usage, followed by domain, return details, and benefit. Every sentence adds value, though slightly verbose for the conciseness ideal. It remains informative without unnecessary repetition.

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 single parameter and no output schema, the description adequately explains expected outputs and domain constraints. It covers return types, data sources, and tool efficiency. Missing details on error handling or unsupported claims, but the open-world hint implies graceful handling of incomplete knowledge.

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

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

Schema coverage is 100% with a description for the 'claim' parameter. The description adds extra constraints by stating the domain of supported claims (company-financial), which is not in the schema. This clarifies valid input scope beyond what the schema provides, earning a 4 above the baseline.

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

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

The description provides a clear and specific purpose: natural-language claim verification against authoritative sources, with concrete examples like 'Is it true that...'. It distinguishes itself from sibling tools by focusing on factual claim verification with a verdict output, which is unique among the listed tools.

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

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

The description explicitly states when to use the tool: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also implicitly defines limitations by specifying 'v1 supports company-financial claims', guiding the agent to avoid non-financial or non-company claims.

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