Close Crm

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to repeat those. It adds value by describing the multi-model probing behavior, return format (score, confidence, signals, raw_response, combined view), and cost implications (default free, Anthropic requires own key). No contradiction with annotations.

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

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

The description is a concise three-sentence paragraph that front-loads the action and key output. Every sentence adds essential information—scope, scoring, cost, and use cases—with no wasted words or redundancy.

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

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

Despite lacking an output schema, the description sufficiently explains the return format (per-model and combined). It covers all parameters, use cases, and behavioral details. The description is complete for a probing tool of moderate complexity.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description adds meaning beyond schema: explains default model, optional Anthropic key, and the return structure. This provides helpful context not present in the schema's parameter descriptions 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 probes LLMs for knowledge about an entity and scores visibility (0-100) per model. It distinctively positions itself for AI-marketing audits, pre-launch brand checks, and competitive monitoring, differentiating it from sibling tools like ask_pipeworx or bet_research which serve different purposes.

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

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

The description provides clear usage context: when to use for AI-marketing audits, brand checks, and competitive monitoring. It explains default model and optional Anthropic key, giving good guidance. However, it lacks explicit when-not-to-use or comparisons with specific sibling alternatives, which would make it a 5.

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

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive. Description adds valuable context: routes to 4,552 tools across 1,160 sources, fills arguments, returns structured answer with stable citation URIs. No contradiction with annotations.

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

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

The description is front-loaded with the key directive, but is somewhat lengthy and includes a list of examples that could be trimmed. However, the structure is logical: directive, explanation, usage guidance, examples, alternatives.

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 (routing to thousands of sources), the description is quite complete: explains routing behavior, citation format, and when to use alternatives. No output schema exists, but description hints at return structure. Covers main aspects adequately.

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

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

Schema has 6 parameters, all with descriptions as aliases for 'question'. 100% schema coverage. Description provides example questions but doesn't add much semantic detail beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly defines the tool's purpose: answering factual questions by routing to a vast collection of authoritative sources. It specifies the verb 'ask' and resource 'Pipeworx', and differentiates from siblings like ask_pipeworx_grounded and deep_research. Many concrete examples are provided.

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 'PREFER OVER WEB SEARCH' and 'START HERE for most questions'. Provides clear when-to-use and when-not-to-use guidance, including stepping up to ask_pipeworx_grounded or deep_research for specific needs. Also covers typical query patterns like 'what is', 'look up', etc.

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

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

Adds significant context beyond annotations: describes extraction process, refusal reasons, cost impact, and that answers are limited to tool result. 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?

Concise yet fully informative. Key concepts front-loaded, every sentence serves a purpose, 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 complexity (many tools, no output schema), the description completely covers behavior, failure modes, and return format, enabling accurate tool selection.

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 alias descriptions. Description adds context about how the question is used (to fetch then extract), but it's not essential. Baseline 3, plus extra value gives 4.

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

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

The description clearly states it is a 'hallucination-resistant answer mode for high-stakes reads,' distinguishing it from sibling 'ask_pipeworx' by explaining the grounded extraction behavior.

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

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

Explicitly tells when to use (quotations, citations, high-stakes) and when to prefer alternative ('prefer ask_pipeworx for casual lookups').

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

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

Annotations indicate safe, idempotent, non-destructive behavior. Description adds extensive behavioral details: resolver contract, parent event extraction, news fields, safety mechanisms for low-confidence matches, closed markets, wide spreads, and resolution-rule risk. No contradictions.

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

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

The description is very long and detailed, which compromises conciseness. It front-loads purpose but dives into many specifics that could be summarized or structured better. Still informative.

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

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

Given the tool's complexity and lack of output schema, the description fully explains all response shapes, edge cases, and internal logic. It covers resolver confidence, parent events, news fallbacks, and safety measures, making it complete.

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

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

Schema covers all parameters with descriptions. The description adds context like recommended defaults (include_raw: false) and explains the market input flexibility beyond the schema. Slightly enhances the schema information.

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

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

The description clearly states it researches Polymarket bets by pulling Pipeworx data. It provides specific input types and use cases, and distinguishes from siblings like polymarket_edges and polymarket_arbitrage.

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

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

Explicitly lists use cases like 'should I bet on X' and gives examples of fan-outs. However, it does not explicitly state when not to use this tool versus alternatives, though the context is clear.

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

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is clear. The description adds value by detailing the return payload (full detail, specific fields), which is not present in annotations.

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

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

Two sentences that cover purpose, ID format, and return fields with no wasted words. Front-loaded with the core action.

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

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

For a simple retrieval tool with full annotations, the description covers the return payload adequately. It lacks information about error cases or pagination, but these are unlikely for a single object fetch.

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

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

Schema coverage is 100%, so the description does not need to add much for parameters. It reinforces the 'lead_id' parameter by mentioning the ID format, but adds no new semantic 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 retrieves a single lead by ID, with specific verb 'Get' and resource 'lead'. It lists returned fields, distinguishing it from sibling listing tools like 'close_search_leads' which return multiple leads.

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 when you have a specific lead ID, and the ID format example helps. However, it does not explicitly state when not to use this tool or compare to alternatives like search tools.

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

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

The description discloses key behavioral traits beyond the annotations: it specifies the return structure (data array with id, _type, type, date_created, type-specific fields, has_more, total_results) and pagination behavior. No contradiction with annotations (readOnlyHint, idempotentHint, destructiveHint).

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, with two short sentences. The first sentence front-loads the primary purpose and types of activities, and the second adds requirements and pagination. 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?

Given the lack of an output schema, the description covers the essential aspects: what the tool does, required parameters, pagination, and return structure. It is complete for a listing tool but could mention ordering or error cases for full 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?

The schema already describes all four parameters thoroughly (100% coverage). The description merely restates the need for lead_id and pagination parameters, adding no new semantic meaning beyond what the schema provides.

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

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

The description uses a specific verb 'List' and resource 'activities for a lead', clearly enumerates the types of activities (calls, emails, notes, etc.), and distinguishes itself from sibling tools like close_list_contacts or close_list_opportunities by focusing on activities.

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 the required parameter 'lead_id' and explains pagination with '_limit' and '_skip', providing clear guidance on how to use the tool. However, it does not mention when not to use it or alternatives, such as using close_search_leads for filtered searches.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true. The description adds structural details (return fields, pagination metadata) and optional filtering, which go beyond annotations. No contradictions.

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

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

Two well-structured sentences front-load the purpose and return structure. Every sentence adds value with no unnecessary words. Efficient and 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?

Despite no output schema, the description thoroughly explains the return format (data array with specific fields, has_more, total_results) and pagination behavior. For a list endpoint with 4 params, this is fully adequate.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by stating lead_id is optional for filtering, _limit defaults to 100 with max 200, and _skip defaults to 0. These details improve understanding beyond the schema.

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

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

The description clearly states it lists contacts in Close, specifies the return structure (data array with fields, has_more, total_results), and mentions filtering and pagination. It distinguishes from sibling tools like close_get_lead and close_search_leads by focusing on listing contacts with optional lead filter.

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 guidance on optional lead_id filtering and pagination with _limit/_skip, including default and max values. Does not explicitly compare to siblings or state when not to use, but context is sufficient for typical use.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. Description adds value by detailing the returned data structure (data array with fields, has_more, total_results) and explaining the effect of parameters like lead_id and pagination, which annotations don't cover.

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 efficiently cover purpose, return structure, and parameter usage without redundancy. Every sentence is essential and well-structured.

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

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

Despite no output schema, the description fully explains the return format and pagination. It covers all necessary details for an agent to use the tool correctly, given the simplicity of the tool and the presence of comprehensive annotations.

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

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

Schema descriptions cover all parameters (100% coverage). Description adds context beyond schema: explains that lead_id scopes to one lead or omits for all, and that _limit/__skip are for pagination. This enriches parameter semantics beyond the raw schema descriptions.

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

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

The description clearly states the tool lists opportunities (pipeline deals) in Close, specifies the returned fields, and distinguishes it from sibling tools like close_list_contacts and close_list_activities by focusing on opportunities.

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

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

Provides clear guidance on when to use lead_id for scoping to one lead versus omitting for cross-organization listing, and explains pagination with _limit/_skip. Does not explicitly mention when not to use or compare with siblings, but sufficiently directs usage.

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

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

Annotations indicate read-only, idempotent, and non-destructive behavior. The description adds behavioral context by specifying the returned data (user ID, name, email, organizations) and the requirement of an API key, enhancing transparency beyond annotations.

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

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

Two sentences, front-loaded with action and returns, no unnecessary words. Every sentence serves a purpose.

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

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

The tool has no output schema, but the description explicitly lists return fields (user ID, name, email, organizations). Given the tool's simplicity, this provides complete context for an agent to understand what it returns.

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

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

The single parameter '_apiKey' is described in the schema as 'Close API key (Settings → API Keys).' With 100% schema coverage, the description provides minimal added meaning, but the source hint is useful. 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 retrieves the current Close user and organization, listing specific return fields (user ID, name, email, organizations). It distinguishes itself from sibling tools by specifying its unique purpose.

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 this to verify the key works and discover your organization context,' providing clear when-to-use guidance. It does not discuss alternatives, but the tool's simplicity makes that unnecessary.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. Description adds return format (data array with fields, has_more, total_results) and pagination details, adding value beyond annotations.

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

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

Two dense sentences with no wasted words. Front-loaded with purpose and includes essential details in a compact structure.

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

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

Despite no output schema, description explains return fields, pagination, and query capabilities. Covers all necessary aspects 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?

All parameters are described in schema (100% coverage). Description enhances with query syntax examples and behavior when omitting query. Adds meaning beyond schema.

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

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

Clearly states the tool searches or lists leads using Close's query language, specifying the resource (leads/companies/accounts) and actions. Distinguishes from siblings like close_get_lead and close_list_contacts.

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 examples of query syntax and explains that omitting query lists all leads. Could be more explicit about when not to use, but context from sibling tools implies alternatives.

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

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

Annotations already declare idempotent, read-only, non-destructive behavior. Description adds value by detailing data sources (SEC EDGAR, FAERS), handling of fiscal years, and result sorting. 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?

Description is front-loaded with common query phrases and is detailed yet efficient. However, it could be slightly more concise by removing some repeated examples. Still earns its place with every sentence adding 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 covers return data (paired data, citation URIs) and sorting. Missing details on citation format or exact primary metric, but overall complete for a tool with simple parameters and clear annotations.

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

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

Schema covers 100% of parameters. Description enriches with per-type data details (revenue, net income for companies; adverse events for drugs) and sorting behavior, going beyond the basic schema descriptions.

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

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

The description uses specific verbs like 'side-by-side comparison' and lists example queries, clearly distinguishing from siblings by stating 'ALWAYS PREFER over sequential single-pack lookups'. It precisely defines the resource (companies or drugs) and the action (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?

Explicitly provides when to use this tool (comparisons, rankings) and when not to (sequential lookups). Offers concrete examples and alternatives (single-pack lookups), leaving no ambiguity for an AI agent.

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

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

Beyond annotations (readOnly, openWorld, idempotent), the description reveals it uses structured data only, returns findings with evidence and citations, gaps array for unanswered facets, and latency expectations (15-60s). 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 slightly lengthy but well-structured, starting with critical account info, then functionality, use cases, and comparisons. Every sentence adds value, though some redundancy with schema descriptions 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?

Fully covers the tool's purpose, behavior, input requirements (account, depth), output format (findings packet), limitations (empty gaps for news), latency, and alternatives. Despite no output schema, the return structure is clearly described.

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

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

Schema coverage is 100% with good descriptions. The description reinforces the depth parameter's meaning (number of facets) and question parameter's suitability for broad queries, adding context but not significantly new information 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 performs grounded multi-source research across structured data sources, decomposing questions into facets and routing to tools in parallel. It distinguishes from siblings like ask_pipeworx for single lookups and breaking news.

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

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

Explicitly states when to use (broad/multi-part questions over structured data) and when not to (single lookup, breaking news), providing alternatives (ask_pipeworx). Also notes account requirements and that thorough depth requires a paid plan.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds valuable behavioral details: returns top-N relevant tools with full input schemas and curated examples, ready to call directly. 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 concise, front-loading the purpose and usage guidance. Every sentence contributes value, though it could be slightly tighter. Structurally sound.

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

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

Even without an output schema, the description explains what the tool returns (top-N tools with schemas and examples). Given the tool's purpose as a discovery mechanism, this is sufficient for an agent to understand the expected response.

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

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

Schema description coverage is 100%, so the schema already documents all parameters and their aliases. The description reinforces this with examples and context, but the schema carries the main burden. 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 finds tools by describing data or task, listing specific domains (SEC filings, financials, FDA, etc.). It distinguishes from sibling tools (e.g., specific tools like close_get_lead) by being a discovery tool for browsing the available option set.

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 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This provides strong guidance on when to use, though it could be improved by explicitly stating when not to use (e.g., if the specific tool is already known).

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. The description adds significant context: it fans out across multiple sources, returns structured data (e.g., 'recent_filings (up to 5)'), and discloses the patent soft-fail ('USPTO PatentsView API sunset May 2025'). It does not cover every nuance like error handling, but goes well beyond annotations.

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

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

The description is dense but every sentence serves a purpose: example queries, preferred usage, data sources, return structure, caveats, and input requirements. It is front-loaded with the core directive and efficiently packs information without redundancy.

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

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

Given the high complexity (multiple data sources) and lack of output schema, the description provides detailed return items (filings with URIs, fundamentals fields, patents, news, LEI). It covers input constraints, behavior, and pitfalls. Lacks exact formatting for some fields but is sufficient for an agent to understand and use the output.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds clarity by specifying that 'value' accepts ticker or zero-padded CIK and reiterates that names are not supported, which reinforces the schema constraints. This is slightly above the baseline of 3 for high coverage.

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

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

The description clearly states the tool provides a 'full cross-source profile of a US public company in ONE parallel call' with specific examples ('Tell me about X', 'research Acme'). It distinguishes from siblings by explicitly preferring this tool over chaining single-pack lookups and directing name-based queries to 'resolve_entity'.

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

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

Explicitly states when to use: 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' Also provides a clear alternative: 'names not supported (use resolve_entity first).' This gives the agent direct guidance on 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?

Annotations indicate destructiveHint true and idempotentHint true. Description adds behavioral context about when deletion is appropriate and pairs with other tools, but no major disclosure beyond annotations.

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

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

Two sentences, front-loaded with core action, no superfluous text.

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

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

Single parameter with full schema description, annotations present, no output schema needed. Description fully covers tool usage and context.

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

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

Schema coverage is 100% with the 'key' parameter described as 'Memory key to delete'. Description adds no further 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?

Description clearly states 'Delete a previously stored memory by key' with specific verb and resource. Distinguishes from sibling tools 'remember' and 'recall'.

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

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

Provides explicit usage context: 'Use when context is stale, the task is done, or you want to clear sensitive data... Pair with remember and recall.'

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it's safe. Description adds behavioral context: fetches the page, extracts title/description/key links, outputs standard llms.txt format. 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 concise and well-structured: purpose first, then process, output format, and use cases. No unnecessary sentences; every sentence adds value.

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

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

Given no output schema, description fully explains the output format (standard llms.txt markdown, ready to drop at site-root/llms.txt) and the high-level process. For a tool with two parameters and clear annotations, this is complete.

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

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

Schema coverage is 100%, with descriptions for both url and max_links. Description does not add further semantic value beyond what schema provides, so 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 explicitly states the tool generates an llms.txt file for any URL, specifies the process (fetch, extract, emit markdown), and gives concrete use cases. It clearly distinguishes from sibling tools like ai_visibility_check or scan_competitor_ai_presence by focusing on llms.txt generation.

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

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

Description lists three explicit use cases: indexing a client's site, drafting llms.txt for own project, auditing competitor. Provides clear context on when to use, though it does not mention when NOT to use or suggest alternatives.

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

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

Adds beyond annotations by specifying default 'active' subscriptions and exact return fields. No contradictions with readOnlyHint=true, 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?

Two sentences: first states purpose and output, second gives usage guidance. No wasted words, 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?

For a simple list tool with one optional parameter, no nested objects, and no output schema, the description covers purpose, return fields, and usage scenario adequately.

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

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

Schema coverage is 100% for the single parameter include_inactive. Description implies default behavior (active only) but does not restate parameter details. Baseline 3 is appropriate.

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

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

Description explicitly states 'List the caller's active subscriptions' and enumerates return fields, clearly differentiating 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?

States when to use: 'review what you're monitoring before adding more or to find an id to cancel'. Provides clear context but does not mention when not to use.

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

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

The description adds behavioral context beyond the annotations, such as rate limits, quota-free usage, and the fact that the team reads digests daily. It implicitly confirms non-destructiveness and no side effects, which aligns with the annotations (destructiveHint=false, etc.).

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

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

The description is concise (5-6 sentences) and front-loaded with the core purpose. It uses clear, structured language with inline definitions for feedback types. Every sentence adds value, no redundancy or fluff.

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

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

The description is fully complete given the tool's simplicity. It covers purpose, usage scenarios, parameter guidance, constraints, and output expectations (no output schema needed since feedback is one-way). The context signals (3 params, 2 required, enums, nested objects) are all addressed.

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

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

The description adds significant meaning beyond the input schema. It explains the enum values for 'type' in practical terms (bug = wrong data, etc.), advises on message content (specific, no user prompts), and adds a 2000-character max constraint not in the schema. Since schema coverage is 100%, the description still enhances understanding.

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

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

The description clearly states the tool's purpose: telling the Pipeworx team about bugs, missing features, data gaps, or praise. It distinguishes itself from sibling tools (none of which are for feedback) by specifying the exact types of feedback and use cases.

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 feedback type (bug, feature/data_gap, praise) and gives instructions on how to write the message (describe in terms of tools/packs, no user prompts). It also mentions rate limits (5 per identifier per day) and that the tool is free and does not count against quota.

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

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

Beyond annotations (readOnlyHint, idempotentHint), the description adds: derivation from CF analytics-engine, no PII, caching behavior (5min-1h), and data shape (pack, tool, count). Fully transparent.

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

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

Four sentences: first states what it does, second lists use cases, third describes data origin and privacy, fourth mentions caching. No wasted words, front-loaded with key info.

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?

While no output schema is given, the description mentions return elements (top tools, top packs, volume). It lacks exact structure but is sufficient for a straightforward aggregation tool. Annotations cover safety and side effects.

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 and description. The description adds semantic guidance: shorter windows for hot topics, longer for steady-state. This adds value beyond the schema.

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

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

The description clearly states the tool returns top tools, top packs, and total call volume over a window. It distinguishes itself from sibling tools like ask_pipeworx by focusing on aggregation statistics rather than querying.

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

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

Three specific use cases are listed, providing clear context for when to use the tool. It does not explicitly mention when not to use, but the unique functionality makes this less necessary.

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

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

Annotations already indicate safe read-only, idempotent behavior. The description adds extensive details: semantic anchor (Jaccard similarity ≥0.30), partition filter (placeholder slugs), fill check against live CLOB depth, and output structure (opportunities array with gap_pp, suggested_trade, etc.). It explains edge cases like skipped_low_similarity and when not to trade, far exceeding what annotations provide.

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

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

The description is well-structured with clear sections for each mode and technical details. However, it is somewhat lengthy; condensing the explanation of semantic anchor and partition filter could improve conciseness without losing essential information. Every sentence adds value, but the length burdens the 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 complexity (multiple modes, fill checks, edge cases) and the lack of an output schema, the description thoroughly explains the output structure and failure conditions. It also references the related tool polymarket_fill_risk for custom sizing, ensuring the agent has complete context 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?

Both parameters have descriptions in the schema (100% coverage). The description adds meaning by explaining what to pass for each parameter (slug/URL for event, seed question for topic), giving examples, and detailing the behavioral difference between modes. This goes beyond the schema to help the agent choose and format parameters correctly.

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

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

The description clearly states it finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes from siblings like polymarket_edges by naming specific methods and modes (event, topic, trending_scan). The verb 'Find' and resource 'Polymarket arbitrage opportunities' are specific and informative.

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: call with no args for trending scan, pass event for per-event check, or topic for cross-event scan. It recommends event mode for a specific market and explains when to use polymarket_fill_risk for custom sizing. However, it does not explicitly contrast with sibling tools like polymarket_edges or polymarket_edge_tracker, missing some cross-tool selection guidance.

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

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

The description provides exhaustive behavioral details beyond annotations, including caching, response structure (by_segment, diagnostics), model families with mathematical conditions, gate criteria, and knob effects. It fully discloses behavior without contradicting annotations.

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

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

The description is lengthy and detailed, but the structure is front-loaded with purpose and organized by segments. While not concise, the verbosity is justified by the tool's complexity. A shorter version might omit necessary detail.

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

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

The description covers all aspects needed: purpose, input knobs, output structure (including diagnostics for empty segments), model explanations, and caching. Despite no output schema, the clarity of response fields is sufficient 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%, so baseline is 3. The description adds contextual usage examples for parameters like min_liquidity and max_spread_pp (e.g., 'Set to 5000 to drop thin-book opportunities...'), which goes beyond schema descriptions. Some parameters are explained in aggregate, but the additional context justifies a 4.

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

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

The description clearly states the tool scans Polymarket markets to find opportunities where Pipeworx data disagrees with market price, explicitly targeting 'what should I bet on today'. It uses specific verbs and resources, and the detailed explanation of three opportunity segments inherently distinguishes it from sibling tools like polymarket_arbitrage.

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

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

The description implies usage for daily betting opportunity discovery but does not explicitly state when to avoid this tool or mention alternatives. Sibling tools are present but not contrasted. The context is clear, but no when-not-to-use guidance is provided.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint true; description adds significant behavioral detail: data comes from daily snapshots, TTL is 60 days, decay computed from daily closes not intraday, and explains snapshot gaps. This fully addresses behavioral traits beyond annotations.

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

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

The description is dense but front-loaded with the core question. Every sentence adds value, though it lacks paragraph breaks. It efficiently packs response structure and limits into a single block.

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

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

No output schema is provided, but the description fully details the response structure (tracked[], expired[], snapshot_dates[]), meaning of each field, and associated limits. This is complete for a telemetry 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?

Input schema has 100% coverage with descriptions. The description adds context by reiterating defaults (14 days, '1wk' window), the clamp range (2-30), and explaining that 'window' refers to snapshot family. This adds meaning beyond schema.

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

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

The description clearly states the tool provides 'edge persistence and decay telemetry' and answers the specific question 'how long has this edge existed and is it shrinking?' It distinguishes from sibling tool 'polymarket_edges' by focusing on temporal analysis rather than current snapshots.

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

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

The description gives implicit usage guidance by contrasting a fresh wide edge with a 3-week-old one, indicating when this tool is valuable. It also mentions limits like TTL and snapshot gaps, but doesn't explicitly state when not to use it or list alternatives.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds substantial behavioral context: it walks the order book ladder, returns specific fields like top_of_book, vwap_fill_price, slippage, shares_filled, and warns about forced directional risk. No contradiction.

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

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

The description is long but well-structured into sections for single-market, basket, and usage guidelines. It is dense with information but not wasteful. Minor issue: uses all-caps for emphasis, which is a bit loud but functional. Could be slightly more concise, but still effective.

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

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

For a complex tool with two modes and no output schema, the description is very complete. It lists all output fields (top_of_book, vwap_fill_price, slippage_pp, etc.) and explains the risks (partial fills, forced directional risk). It provides enough context for an agent to understand the tool fully.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant meaning: it explains different interpretations of size_usd for single-market vs basket (max spend vs target proceeds vs settlement notional), side default auto logic based on partition sum, and specifies range and defaults. This goes beyond the schema's descriptions.

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

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

The description clearly states the tool's purpose as a 'realizable-vs-theoretical edge check against live CLOB order-book depth' and distinguishes between single-market and basket modes. It also contrasts with sibling tools like polymarket_arbitrage and polymarket_edges by specifying it should be used before acting on those signals.

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

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

Explicitly states when to use: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains the reasoning (theoretical overround not capturable, partial fills causing directional risk), providing 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 declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds significant context about compatibility_warning conditions, temporal_alignment, and skipped comparison counters, going well beyond the annotations.

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

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

The description is thorough and well-structured with clear sections, but it is relatively long. Some redundancy exists (e.g., may have detailed explanations that could be tightened). Still, every part adds value.

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

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

Given no output schema, the description fully explains the response structure, safety fields, and edge cases. It covers input, output, and when the data is meaningful, making it completely adequate 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 value by explaining the two selection modes and listing the exact topic shortcuts. This provides context beyond the schema descriptions.

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

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

The description clearly states the tool computes cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes from siblings like polymarket_arbitrage and polymarket_edges by specifying the two-venue 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 explains two modes (topic macro shortcuts vs explicit tickers) and provides safety fields (compatibility_warning, temporal_alignment) that indicate when results are not meaningful. It could be more explicit about when to use alternatives, 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 readOnly and idempotent; description adds that listing all keys is achieved by omitting the argument and confirms scoping, with no contradiction.

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

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

Three concise sentences that front-load the main action and include usage, scope, and pairing; 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?

Covers purpose, usage, scope, and pairing; no output schema but tool is simple and description implies return values (value or list of keys); slight lack of explicit return format.

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 schema description already explains the 'key' parameter including omit behavior; description adds minimal extra meaning beyond pairing with remember.

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 ('Retrieve' or 'list') and resource ('value previously saved via remember'), and distinguishes from sibling tools 'remember' and 'forget' by naming them.

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

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

Explicitly states when to use ('look up context the agent stored earlier'), what not to use for (implied by pairing with remember/forget), and provides context about scoping to user identifier.

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

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

Description discloses mark_read behavior which mutates state, but annotations declare readOnlyHint=true, creating a contradiction. Per rules, score is 1.

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

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

Three sentences, no redundant words. Front-loaded with key purpose and return fields. 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?

Covers return fields, filtering, mark_read behavior, polling vs. REST alternative. Adequate for a read tool with no output schema.

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

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

Schema coverage is 100% with parameter descriptions. Description adds practical usage context (e.g., 'Set mark_read:true to flag returned events read so the next call only shows newer ones') beyond schema doc.

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?

Title and description clearly state the tool pulls fired events from subscription feed, specifying return fields and filtering options. Differentiates from siblings by focusing on recent alerts from persisted feed.

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?

Describes when to use (polling) and provides an alternative (direct REST endpoint). Does not explicitly state when not to use, but gives context that polling works fine.

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 provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds details: fans out to SEC EDGAR, GDELT/GNews (with fallback), USPTO (PatentsView sunset noted), relative date parsing, and return structure including citation URIs.

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

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

The description is dense but well-organized, starting with usage examples, then data sources, fallbacks, parameter details, and cross-reference. Could benefit from bullet points for clarity, but it's efficient 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 no output schema, description covers return structure (changes[] grouped by source, total_changes, citation URIs). Missing output schema is compensated by this description. Complexity of multi-source polling and fallback is fully explained.

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

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

Schema coverage is 100%, but description adds relative shorthand examples ('7d', '30d', '3m', '1y') for 'since', explains 'value' accepts ticker or CIK, and reinforces that 'type' only supports 'company'. These enrich parameter understanding.

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

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

The description clearly states the tool returns a 'change feed for a company in the last N days/weeks/months', with specific verb 'change feed' and resource 'company'. It distinguishes from sibling 'entity_profile' which returns a 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?

Explicit examples of queries ('What's new with X', 'latest on Y') and a direct alternative: 'Use entity_profile instead when you want the static profile...'. Also explains fallback from GDELT to GNews.

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

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

Adds context beyond annotations: scoped by identifier, persistence details (authenticated persistent, anonymous 24h), and key-value storage. 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?

Every sentence adds value; front-loaded with core purpose. No redundancy, well-structured despite length.

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

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

Covers persistence, scoping, usage, and related tools. No output schema needed; description fully addresses agent's needs for understanding tool behavior.

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

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

Schema coverage is 100%, so baseline 3. Description adds minor context for key (example patterns) and value (types of content), not significantly enhancing schema information.

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 saves data for later reuse, using specific verbs like 'save' and 'store' with a key-value pair resource. It explicitly distinguishes from siblings 'recall' and 'forget'.

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

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

Provides clear guidance on when to use (discovering something worth carrying forward) with concrete examples. Mentions pairing with recall and forget, but lacks explicit when-not-to-use instructions.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context that each call cascades through several lookup endpoints and replaces 2-3 manual lookups, enriching behavioral understanding without contradiction.

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

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

The description is concise and front-loaded with example queries followed by purpose, but it is a single paragraph. While efficient, breaking into structured points could improve readability. Still, it earns its place with no redundancy.

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

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

For a tool with only 2 parameters and no output schema, the description is remarkably complete. It explains return values, input variants, internal cascading, and usage priority. No gaps are apparent given the tool's simplicity.

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 significant meaning: it explains the return structure for each type (ticker, CIK for company; RxCUI for drug) and acceptable input formats, going well beyond the schema's minimal descriptions.

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

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

The description clearly states the tool resolves a user-spoken name to a canonical identifier, with specific examples like 'What's the ticker for...'. It distinguishes itself from siblings by focusing solely on name-to-ID resolution, which is a unique purpose.

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', providing clear usage context. It also details supported types and return values, guiding when to use this tool over alternatives.

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds that it probes each entity with ai_visibility_check, ranks results, returns score/confidence/signal density, and treats first entity as subject. 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?

Two sentences, front-loaded with main purpose, then details. Every word earns its place. 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?

No output schema, but description explains return value (ranked list with score, confidence, signal density). Covers all parameters, use case, and internal behavior (multiple probes). Complete for 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%, baseline 3. Description adds meaning: entities array size 2-8, first as subject; models default to workers-ai, optional anthropic requires _apiKey; context for disambiguation. Adds value beyond schema.

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

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

Description clearly states the tool compares AI visibility across multiple entities, uses specific verb 'Compare' and resource 'AI visibility'. It distinguishes from siblings like ai_visibility_check (single entity) and compare_entities (generic comparison).

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

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

Provides a concrete use case for competitive AI-marketing audits with example question. While it doesn't explicitly state when not to use or list alternatives, the context makes it clear. No exclusions but good 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?

Adds significant behavioral context beyond annotations: mentions fan-out to two services, potential delay (5-30s on first bundlephobia measurement), graceful degradation with sources_failed reporting, and return structure. No contradiction with readOnlyHint/idempotentHint.

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

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

Description is relatively long but each sentence adds value: purpose, use cases, scope, behavior, output. Front-loaded with core purpose. Could be slightly tighter but well-organized.

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

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

Given complexity (two services, partial failures, no output schema) and moderate parameter count, the description covers all needed context: ecosystem, default behavior, return summary, error handling, and use cases. Complete for an agent to use correctly.

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

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

Schema coverage is 100% and describes both parameters. Description adds extra meaning: scoped packages accepted, default to latest version when omitted, and ecosystem context. Baseline 3, with extra value justifies 4.

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

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

The description clearly states the tool's purpose as a composite check for adding npm packages, naming specific data sources (deps.dev, bundlephobia) and use cases (safety, popularity, size). It is distinct from sibling tools, none of which perform dependency scanning.

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 when to use: 'whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also provides ecosystem limitation (NPM only in v1) and fallback options (PyPI/Maven etc. via deps.dev).

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

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds technical specifics: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, and a 200K char limit with truncation warning, providing valuable behavioral context beyond annotations.

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

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

The description is concise with 4-5 sentences, each serving a purpose. It is front-loaded with the core purpose, and every sentence contributes unique information without redundancy.

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

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

Given the tool's complexity (semantic search with parameters and technical details), the description covers purpose, usage, pairing, technical specifics, limits, and return format. No output schema exists, but the description adequately describes what is returned.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by providing practical examples for the query parameter and stating the truncation behavior for the text parameter, moving it above baseline.

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

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

The description explicitly states the tool performs semantic search inside a fetched record, returning top passages with offsets and scores. It clearly distinguishes from siblings by mentioning ask_pipeworx_grounded as a complementary 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 explicitly says to use when the record is too big for the prompt, saving context. It also provides a pairing pattern with ask_pipeworx_grounded, giving clear when-to-use and alternative guidance.

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

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

The description goes beyond annotations by detailing account requirements, supported subscription types with parameter examples, delivery channel constraints (10/day SMS cap, webhook auto-disable), and the one-time webhook secret return. No contradictions with annotations are present.

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 and front-loaded, starting with the core action. It is somewhat lengthy but each sentence provides necessary information. Minor 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 the tool's complexity (3 params, nested objects, 1 enum), the description covers all aspects: purpose, return value, prerequisites, types, delivery channels, and limitations. No output schema exists, but the return value is stated. The context is fully adequate.

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

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

Although the input schema has 100% coverage, the description enriches parameters with real-world examples and explanations (e.g., meaning of item codes in sec_8k, requirement for phone verification, webhook signature details). This adds significant value beyond the schema.

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

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

The description clearly states the tool creates a subscription to a live-data event stream and returns a subscription id. It is well-differentiated from sibling tools like list_subscriptions and unsubscribe.

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

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

The description provides clear context on when to use the tool (e.g., for proactive monitoring) and specifies account requirements (Pipeworx OAuth account). However, it does not explicitly mention when not to use it or directly compare 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 already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint. The description adds behavioral context: it returns example questions and tool shapes, not actual data execution, which aligns with and supplements the annotations.

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

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

The description is front-loaded with common user phrasings and structured into a clear purpose, functionality, and usage guidance. Every sentence adds value without redundancy for a tool of this complexity.

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

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

Despite no output schema, the description explains the return format sufficiently ('category-bucketed example questions, each with the exact tool + argument shape'). It covers all contextual needs for an onboarding tool with a single optional parameter.

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

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

Schema coverage is 100% with parameter description listing possible values. The description adds practical examples ('finance', 'pharma', 'betting') and clarifies the effect of omitting the parameter, beyond what the schema provides.

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

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

The description clearly states it returns category-bucketed example questions with tool+argument shapes, serving as the onboarding entry point. It distinguishes from sibling tools like ask_pipeworx and discover_tools by being the first step to learn what Pipeworx can do.

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

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

Explicitly tells when to use: 'when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools.' It also explains calling with no arguments for full spread or with a topic to focus, providing 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?

Discloses that the row is deactivated, not deleted, preserving historical events. This adds critical context beyond annotations (idempotentHint, destructiveHint), explaining the exact behavioral consequences of invoking the tool.

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 action. Every sentence adds value: action, ownership constraint, behavioral side effect, and connection to related tool. No wasted words.

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

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

Given single parameter, good annotations (readOnlyHint, idempotentHint, destructiveHint), and no output schema, the description fully covers how the tool works, its side effects, and relation to recent_alerts. Nothing missing.

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

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

Input schema already describes the 'id' parameter fully (uuid from subscribe). The description reinforces 'by id' but does not add new meaning beyond the schema. Schema coverage is 100%, so baseline 3 is appropriate.

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

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

The description clearly states the verb 'Cancel' and the resource 'subscription by id', distinguishing it from sibling tools like 'subscribe' and 'list_subscriptions'. It explicitly describes the action and 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?

Provides explicit usage condition: ownership enforcement (you can only cancel your own subscriptions). Also contrasts with deletion behavior and explains availability of historical events via 'recent_alerts', guiding when to use this tool vs alternatives.

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

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

Description goes well beyond annotations by detailing supported domains (company-financial), data sources (SEC EDGAR + XBRL), and return format (verdict types, citation, delta). This compensates for the missing output schema and fully informs agent of behavior. No contradiction with annotations.

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

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

Description is concise yet comprehensive, front-loaded with key trigger phrases and purpose, followed by scope, output details, and efficiency claim. No redundant 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 single-parameter tool with strong annotations, the description provides complete contextual coverage: input format, supported domain, data sources, output schema (though not in schema field), and efficiency gains. No significant gaps.

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

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

With 100% schema coverage, description enhances parameter understanding by specifying the domain (company-financial) and providing concrete examples that align with schema's own examples. This helps the agent formulate valid claims.

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 defines the tool's purpose as verifying natural-language factual claims against authoritative sources, specifies the current domain (company-financial), and distinguishes from sibling tools by being a dedicated verification endpoint that replaces multiple sequential calls.

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

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

Description provides explicit use case ('whenever the agent needs to check whether something a user said is factually correct') and explains efficiency benefit over alternative approaches. However, it does not explicitly state when to use alternatives like ask_pipeworx_grounded, so not a full 5.

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