Osf

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive nature. The description adds useful context: default free model, pay-for-Anthropic, return structure (per-model score/confidence/signals/raw_response + combined view). No contradictions.

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

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

Three well-structured sentences: purpose and output, model details and pricing, use cases. Front-loaded with key info, no wasted words.

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

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

Despite having no output schema, the description adequately describes the return structure (per-model + combined view). All parameters are explained, use cases are given, and the tool's behavior is sufficiently documented for selection and invocation.

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

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

With 100% schema coverage, the description still adds value by clarifying the entity parameter with examples, explaining the models array and _apiKey usage, and the context parameter for disambiguation. This provides a richer understanding beyond the schema.

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

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

The description clearly states the tool probes LLMs for brand visibility and scores it (0-100), distinguishing it from siblings like ask_pipeworx or deep_research which are more general Q&A or research tools.

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

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

The description provides clear use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and explains the model selection and API key requirement, but does not explicitly mention when not to use the tool or suggest alternatives for different needs.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral context: it routes to one of 5,743 tools, fills arguments automatically, and returns stable pipeworx:// citation URIs. It could mention rate limits or failure modes, but this is solid 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?

The description is longer than average but front-loaded with the critical guidance 'PREFER OVER WEB SEARCH' and the domain list. The trailing example sentences are repetitive, but each section earns its place by reinforcing when to use the tool.

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

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

The description covers purpose, usage scope, expected input type, and output characteristics (structured answer with citations). Given that there is no output schema, it could describe the return structure in more detail, but for a single-parameter natural-language tool it is largely complete.

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

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

Schema description coverage is 100%: all six parameters are documented as aliases for the same natural-language question. The description reinforces this by giving example queries, but it does not add much semantic meaning beyond what the schema already states. Baseline 3 is appropriate given full schema coverage.

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

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

The description states exactly what the tool does: it routes questions to one of 5,743 tools across 1,500 verified sources and returns structured answers with citations. The verb 'ask' plus resource 'Pipeworx' is clear, and it is explicitly distinguished from web search and other research tools.

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

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

The description gives explicit guidance: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', a list of covered data domains, and concrete example queries. It clearly tells the agent when to use this tool versus general web search.

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

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses that candidate routing improvements are enabled live when under test, that no candidate is currently active, and that the tool matches ask_pipeworx exactly right now. It also explicitly states 'Falls back to nothing' and clarifies it is a full working router, removing any assumption that beta means degraded or partial. This is rich, honest behavioral context.

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

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

The description is front-loaded with the core identity and scoping, then adds current status, usage direction, and fallback behavior in a logical order. It is slightly verbose with specific details like the retirement date and tool count, but every sentence adds useful context. A small amount of redundancy around 'matches exactly' is acceptable given the clarification 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?

There is no output schema, but the description says the response shape is identical to ask_pipeworx, giving an agent a reference for expected results. It also covers current behavior, experimental status, and lack of fallback, which are the most important operational facts. The only minor gap is not describing the actual response format directly or mentioning the sibling ask_pipeworx_grounded, but the stable-router reference mitigates this.

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

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

Schema description coverage is 100%, and the schema already fully documents the six parameters as aliases for the single required 'question' field. The description adds no new parameter-specific semantics beyond saying it has the same arguments as ask_pipeworx. Baseline 3 is appropriate because the structured schema carries the parameter documentation burden.

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

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

The description clearly identifies this as the beta version of ask_pipeworx and defines it as an identical universal router with the same 5,743 tools, arguments, and response shape. It distinguishes itself from the stable ask_pipeworx by emphasizing it is the experimental edge for candidate routing improvements. This gives an agent a concrete, specific picture of what the tool does beyond its name.

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

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

The description explicitly says to 'Use it exactly like ask_pipeworx when you want the newest routing,' naming the stable alternative and the condition for choosing this tool. It also explains that results are compared against the stable router, which clarifies the evaluation role this beta variant plays. This is strong practical guidance for when to invoke it.

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

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

The description goes far beyond the annotations by explaining the internal mechanism: it retrieves data via the same routing as ask_pipeworx but extracts answers exclusively from the tool result. It also discloses the exact return shape, the refusal reason enum, and the extra LLM call cost, giving the agent a clear model of what to expect.

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

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

The description packs a large amount of useful information into a compact, well-structured format. It front-loads the purpose and key differentiator, then covers behavior, return format, use cases, and cost trade-offs with no filler or redundancy.

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

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

Despite having no output schema, the description fully specifies the success response and refusal response, including refusal reason values. Combined with the clear routing guidance, cost note, and input schema, the agent has everything needed to select and invoke the tool correctly.

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

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

Schema description coverage is 100%, and the question parameter is already well documented with its aliases. The description adds no additional parameter-level guidance, but the schema fully handles parameter semantics, so the baseline score of 3 is appropriate.

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

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

The description clearly identifies this as a hallucination-resistant, grounded answer mode distinct from ask_pipeworx and ask_pipeworx_beta. It specifies the resource (Pipeworx grounded answers), the core behavior (extracting answers only from tool results), and the high-stakes use case.

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

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

The description explicitly states when to use this tool ('whenever an answer will be quoted, cited, or acted on') and gives concrete examples of high-stakes domains. It also names the alternative (ask_pipeworx) and tells the agent to prefer it for casual lookups, making the routing decision unambiguous.

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, non-destructive. Description adds extensive behavioral context: resolver contract, parent event extraction, news fallback mechanisms, safety short-circuits for low confidence, closed market handling, wide spread warnings, and cancellation rule parsing. 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?

Extremely detailed but verbose. While every sentence adds value, the description is massive and could benefit from better structure (e.g., sections). Front-loading is good but overall length may overwhelm agents.

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

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

Covers all necessary context given complexity: classifiers, fan-out examples, response shapes, resolver behavior, parent events, news error handling, safety checks, market states, and cancellation rules. No output schema exists, but the description compensates with thorough response format details.

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

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

Schema coverage is 100% with descriptions for all three parameters. The description adds significant meaning: explains market parameter can be slug, URL, or question text; details depth options with examples; clarifies include_raw purpose and size implications.

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

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

The description clearly states the tool researches Polymarket bets by pulling Pipeworx data. It specifies input types (slug, URL, question text) and outputs (evidence packet, market-vs-model comparison). This distinguishes it from sibling tools like polymarket_edges which focus on edge detection.

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

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

Explicitly states use cases: 'should I bet on X', 'what does the data say about Y', 'is there edge in Z'. While not directly contrasting with siblings, the primary usage is clear. Could be improved by explicitly noting when to use alternatives like polymarket_arbitrage.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds data source details (SEC EDGAR/XBRL, FAERS), off-calendar fiscal year handling, and sorting by primary metric.

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?

Extremely concise: triggers in first sentence, then single paragraph covering purpose, preference, data sources, and output. 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?

Covers key aspects: entity types, data sources, sorting, and output format (paired data + citations). Could add more on output structure but sufficient given tool complexity.

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

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

Schema coverage is 100%, but description adds meaningful context: explains enum options (company/drug) with data sources, and values parameter constraints with examples (tickers vs drug names).

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

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

The description clearly states the tool does side-by-side comparison of 2–5 companies or drugs, with specific trigger phrases. It distinguishes from siblings like entity_profile by emphasizing parallel over sequential lookups.

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

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

Explicitly states 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and provides trigger phrases for when to use. Implicitly excludes single entity or more than 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 signal safe, non-destructive, open-world, idempotent behavior; the description then adds rich behavioral detail: account and paid-tier requirements, parallel decomposition, latency expectations, fetchable citation URIs, explicit gaps[] instead of invented answers, contradiction scanning, and semantic excerpting. No annotation contradiction exists.

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

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

The description is long but dense, with the most critical operational fact (account required) front-loaded. It packs substantial behavioral and routing detail without filler, though the depth explanation partially repeats schema content and could be tightened.

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 no output schema, it covers the return packet, citation reliability, gap handling, contradictions, latency, depth variants, auth, and alternatives. An agent has enough context to decide whether to call this tool and what to expect from the result.

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

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

Schema coverage is 100% and the schema already documents both 'question' and the three depth levels with their hop and contradiction behavior. The description reinforces these semantics and adds auth/usage context, but it does not materially add parameter 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 names a specific verb and resource: grounded multi-source research across Pipeworx's structured data sources in one call. It explicitly distinguishes itself from open-web search and from ask_pipeworx, making sibling differentiation immediate.

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

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

It tells the agent exactly when to use it (broad/multi-part questions over structured data) and when not to ('For a single lookup use ask_pipeworx instead'). It even covers the auth prerequisite and fallback for unsigned-in users, which is unusually explicit routing guidance.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false. Description adds behavioral context: returns full schemas with examples, 'no second schema lookup needed'. No contradictions.

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

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

Description is front-loaded with purpose, then usage, then behavior. Each sentence adds value; no redundancy. Slightly long but efficient.

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

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

Given no output schema, description adequately covers return value (tool names, descriptions, schemas). Context signals show moderate complexity; description is complete enough for an agent to invoke correctly.

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

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

Schema coverage is 100% with all parameters described. Description repeats alias info but does not add significant new meaning beyond 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?

Description clearly states the tool discovers tools by describing data or task, listing many domains. It distinguishes from siblings like search_preprints by being about tool discovery, not data search. Verb 'Find' and resource 'tools' are specific.

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 'Call this FIRST when you have many tools available and want to see the option set'. Provides examples of when to use (e.g., look up FDA drugs). Does not explicitly mention when not to use, but 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?

Even though annotations already mark it readOnly/idempotent, the description adds substantial behavioral context: it fans out across multiple sources, returns sources_used/sources_failed, empty sections should be interpreted as genuine 'no data' rather than errors, and private companies yield resolved:false with an explicit notes line. It also discloses the GDELT→GNews fallback and that fda_products will be empty for small-molecule-only companies, which prevents misinterpreting expected outcomes.

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: trigger phrases come first, then a data-source inventory, return sections, and edge cases. It earns its length for such a complex tool. Minor redundancy with the schema and a couple of ambiguous placeholder phrases like 'sorted descending?' and 'recent?' prevent a perfect structure score.

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

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

With no output schema, the description diligently explains return values: cik, company_name, resolved_from/resolved_to, recent_filings with pipeworx URIs, fundamentals, patents, federal_contracts, fda_products, hiring, news, LEI, and sources_used/sources_failed. It also covers input edge cases and expected empty sections. It lacks exact JSON field structure and behavior for unknown public tickers, so it is not fully exhaustive.

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

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

Schema coverage is 100%, and the input schema already documents both parameters, including accepted examples and the interchangeability of 'company' and 'ticker'. The description largely restates these details without adding new parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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

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

The description opens with a clear verb and resource: it produces a 'full cross-source profile of a US public company in ONE parallel call.' It enumerates nine example trigger phrasings ('Tell me about X', 'research Acme', 'brief me on Tesla'), making the intended use immediately recognizable, and distinguishes itself from single-pack SEC/XBRL/news lookups by emphasizing the cross-source, holistic scope.

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

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

It explicitly says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view,' which is a clear routing rule. It also specifies accepted input shapes (ticker, CIK, or company name) and explains that 'type' accepts 'company' or 'ticker' interchangeably, removing ambiguity about when to call this tool.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds context about appropriate scenarios (stale context, completed tasks, sensitive data), which goes 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?

Two well-structured sentences. The first sentence states the primary action; the second provides usage guidance. No unnecessary words.

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

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

For a simple tool with one parameter and no output schema, the description fully covers purpose, usage, and parameter meaning. No gaps or missing information.

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

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

Schema coverage is 100% and already describes the 'key' parameter as 'Memory key to delete'. The description does not add additional details beyond the schema, 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?

The description clearly states the action ('Delete') and the resource ('previously stored memory by key'). It distinguishes from sibling tools like '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 when-to-use conditions: 'when context is stale, the task is done, or you want to clear sensitive data'. It also mentions complementary tools ('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 indicate readOnlyHint and idempotentHint, confirming no side effects. The description adds that the tool fetches the page, extracts content, and outputs a markdown blob. This behavioral context is consistent with annotations and enhances understanding.

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 three sentences long, front-loading the core purpose. It efficiently covers what, why, and how without redundancy, making it easy to parse quickly.

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 tool with two parameters and no output schema, the description is comprehensive. It explains the output format and provides use cases. Minor gaps like error handling do not detract significantly from its completeness.

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

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

Schema coverage is 100%, so the baseline is 3. The description does not add extra meaning beyond what the schema provides for 'url' (any URL) and 'max_links' (max 50, default 25). No additional semantics or examples are given.

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: generating a production-ready llms.txt file for any URL. It specifies the target AI crawlers and the output format, making it distinct from sibling tools like 'ai_visibility_check' or 'scan_competitor_ai_presence' that focus on analysis rather than generation.

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

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

The description explicitly lists three use cases: getting a client's site indexed, drafting for own project, or auditing competitors. While it does not provide negative guidance (when not to use), the context is sufficient for an agent to select 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 declare readOnly, idempotent, and openWorld hints. The description adds that the project is public and lists return fields, providing moderate additional 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 a single sentence that efficiently conveys purpose, target, and return values. No redundant or unnecessary content.

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 tool with one parameter and no output schema, the description is complete. It explains what the tool does, what it returns, and is sufficient for correct agent invocation.

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

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

The schema covers the single parameter 'id' with description and example. The tool description adds an example format but does not significantly expand meaning beyond the schema; baseline 3 is appropriate due to 100% schema coverage.

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

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

The description clearly states it fetches metadata for a single public research project by OSF id, and lists specific returned fields (title, description, category, etc.). It distinguishes from sibling search_projects by focusing on a single project retrieval.

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

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

The description clearly implies usage when you have an OSF id and need project metadata. It does not explicitly state when not to use it or point to alternatives like search_projects, but 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=true, idempotentHint=true, and destructiveHint=false. The description adds useful context on the return fields and the default behavior (active subscriptions), enhancing transparency 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?

Two sentences with no wasted words. The first sentence states the purpose and return fields, the second gives usage guidance. Perfectly concise.

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

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

Given no output schema, the description enumerates return fields. With only one optional parameter fully described in the schema, the description fully captures the tool's behavior and how to use it.

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 adds no extra meaning beyond the schema. The description's mention of 'active' aligns with the schema's default false for include_inactive, but no additional semantics are provided.

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 'List' and the resource 'the caller's active subscriptions', distinguishing it from sibling tools like 'subscribe' and 'unsubscribe' which perform different actions.

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

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

Provides explicit usage guidance: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' This tells when to use it, though it doesn't explicitly mention when not to use it or alternatives.

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

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

Discloses rate limiting (5 per identifier per day), non-quota status, the claim_token workflow, and how the team processes feedback. These details go well beyond the neutral annotations and give the agent a realistic picture of side effects and constraints.

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

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

The description is longer than average but every sentence carries useful info: purpose, usage, exclusions, workflow, rate limits, and cost. It is front-loaded with the core purpose and stays on-topic, though slightly dense.

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

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

Without an output schema, the description adequately explains return behavior (claim_token for unauthenticated filing) and follow-up usage. It covers the tool's full lifecycle from filing to resolution, making it complete for an agent to invoke correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds extra semantic value by explaining the claim_token flow (file without account, later pass token to read status) and clarifying that context identifies the relevant tool/pack/vertical. This goes beyond what the schema descriptions provide.

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

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

The description states the tool's purpose with a specific verb and resource: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It clearly distinguishes itself from sibling tools, all of which focus on research or discovery rather than feedback.

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

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

Provides explicit when-to-use guidance (bug, feature/data_gap, praise), a clear exclusion (tools from other MCP servers), and practical instructions for using claim_token to follow up. This is textbook usage guidance.

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

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

Annotations already declare read-only, idempotent, and non-destructive. The description adds valuable context: data source ('CF analytics-engine'), privacy ('no PII'), cache duration ('cached 5min-1h'), and output format ('(pack, tool, count)'). 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 short paragraphs with bullet points. Every sentence adds value, and the core information (what is returned, window options) is front-loaded. No wasted words.

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

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

Despite no output schema, the description adequately explains the return values (top tools, packs, volume), caching, data source, and privacy. For a single-parameter tool, this is fully sufficient.

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

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

Schema coverage is 100% with a single enum parameter fully described. The description adds context about window semantics (hot vs steady-state) that goes beyond the schema's description, justifying a score above the baseline of 3.

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

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

The description clearly states the tool returns 'top tools, top packs, and total call volume over a recent window'. It uses specific verbs and distinguishes from siblings like 'discover_tools' and 'ask_pipeworx' by focusing on trending aggregate data.

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

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

Three explicit use cases are provided, along with guidance on window selection ('shorter windows surface what's hot right now; longer windows show steady-state demand'). However, it does not explicitly state when not to use this tool or mention alternatives among siblings.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false. The description adds substantial behavioral context beyond annotations: it describes the fill check that prices against live CLOB depth, the semantic anchor for similarity, partition filter for placeholders, and specific conditions when to avoid trading (realizable_edge_pp <= 0). 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 comprehensive and every sentence adds value. It is front-loaded with the main purpose. While it is lengthy, the complexity of the tool justifies the detail. Slightly more structured formatting (e.g., bullet points for modes) could improve readability, but it is 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?

No output schema exists, so the description must cover return values. It does so thoroughly: describes opportunities[] with fields like gap_pp, suggested_trade, reasoning; partition_check in event mode; fill check results including realizable_edge_pp at 1000 shares/leg and thin_legs[]. It also covers error-like signals (skipped_low_similarity, placeholder filtering). The description is complete for the tool's complexity.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds rich meaning: for 'event', it explains slugs and full URLs are accepted; for 'topic', it gives examples and explains cross-event scanning. It also describes internal logic like monotonicity and partition checks, greatly enriching the schema.

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

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

The description clearly states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes between modes (no args, event, topic) and specifies the resource (Polymarket markets) and action (finding arbitrage). It differentiates from sibling tools like polymarket_edges by focusing specifically on arbitrage detection.

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 provides usage guidelines for each mode: 'Call with NO args for a trending_scan...', 'event (recommended for a specific market): pass a Polymarket event slug...', 'topic (for cross-event scanning): pass a seed question...'. It includes examples and warns when not to trade via fill check. It also mentions polymarket_fill_risk for custom sizing, guiding the agent to alternatives.

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

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

The description is extremely transparent, disclosing caching behavior ('Cached 1h at the KV level keyed on all knobs'), the logic behind model families (e.g., 'lognormal barrier from 90d FRED log-returns'), edge calculation ('net of slippage'), and output structure ('by_segment{...}, fed_candidates, _diagnostics'). It goes far beyond the annotations, which only indicate read-only and idempotent traits.

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

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

The description is verbose, with detailed explanations of model families and internal calculations. While front-loaded with the purpose, it could be more concise. The depth is understandable given the tool's complexity, but it could be structured more efficiently for quick scanning.

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

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

Despite the lack of an output schema, the description fully explains the return structure (by_segment segments, fed_candidates, _diagnostics) and the contents of each opportunity (edge_pp_net, kelly_fraction, etc.). It also covers caching, exclusion of Fed bets, and the rationale behind knobs. This provides complete context for an agent to use the tool effectively.

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

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

Schema coverage is 100% with detailed parameter descriptions. The description adds extra meaning, such as explaining that 'min_liquidity' and 'max_spread_pp' are 'Tradeable-edge filters' and providing default values and reasoning (e.g., 'bump for very thin partitions'). This adds value beyond the schema, warranting a score above the baseline of 3.

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

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

The description clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It uses a specific verb ('scan' and 'return') and resource ('Polymarket markets') and distinguishes from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on edge detection from Pipeworx data.

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

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

The description explicitly says it's 'Built for 'what should I bet on today' — agents discover opportunities without paging hundreds of markets.' It provides context on when to use it (discovery) but does not explicitly mention when not to use or alternatives. However, the detail on model families and tradeable-edge knobs helps the agent understand appropriate usage scenarios.

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 substantial behavioral context beyond annotations: it details the response structure (tracked, expired, snapshot_dates), explains computed fields like decay_pp_per_day and trend, clarifies that negative edge_pp_net means SELL YES, and notes limitations like 60-day TTL and snapshot gaps. All consistent with readOnlyHint and 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?

The description is detailed but well-organized, starting with the purpose, then response fields, then limitations. It is slightly verbose but each sentence adds value. Could be tightened slightly without losing clarity.

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

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

Given no output schema, the description thoroughly explains the return values (three arrays with field details and interpretations). It also covers limitations (60-day TTL, snapshot gaps, decay computation). This makes the tool fully understandable without external documentation.

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 default values (days=14, window='1wk'), range (days clamped 2-30), and expands window options (24hr, 1wk, 1mo). This provides practical guidance beyond the schema's brief 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: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It answers the specific question 'how long has this edge existed and is it shrinking?' and distinguishes itself from siblings like polymarket_edges by focusing on temporal persistence and decay.

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

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

The description explains when to use the tool: to understand edge persistence and decay. It implicitly contrasts with polymarket_edges for current edges, but does not explicitly list alternatives or when not to use. The context is clear enough for an agent to decide.

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

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

Annotations already indicate readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. The description adds details about live order-book checking, verdict types (clean/degraded/cannot_fill), and forced directional risk. It warns of the dominant loss mode from partial basket fills, which goes 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 well-organized with clear sections for each mode and ends with usage rationale. While somewhat verbose, every sentence is informative and front-loaded. Could be slightly tighter, but effectively balances detail and 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?

No output schema exists, yet the description comprehensively lists return values for both modes (e.g., top_of_book, vwap_fill_price, verdict for single-market; capture_ratio, profit_usd, thin_legs for basket). It covers when to use, output details, and risk factors, making it fully complete.

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

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

Schema coverage is 100%, but the description adds significant context: mode-dependent interpretations of size_usd (spend vs target proceeds vs settlement notional), default side behavior in basket mode (auto from partition sum), and the REQUIRES constraint for market or event. This enriches 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 defines the tool as a 'realizable-vs-theoretical edge check against live CLOB order-book depth'. It distinctly separates single-market and basket modes, and provides specific metrics returned (verdict, fill details). This distinguishes it from siblings like polymarket_arbitrage by focusing on fill risk.

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

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

Explicit guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. It explains the rationale (theoretical overround not capturable, partial fills create directional risk) and differentiates modes. No explicit 'when not to use', but the positive guidance is comprehensive.

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

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

The description goes far beyond the annotations, disclosing fees, matching behavior, compatibility warnings, skipped comparisons, temporal alignment semantics, and what null means. It also explains that returned pairs can still carry warnings and that spreads are gross, not net tradeable edge. There is no contradiction with the readOnlyHint=true annotation.

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

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

The description is long, but it is well-structured with clear section markers (TWO MODES, RESPONSE, SAFETY FIELDS, codes) and every sentence conveys necessary caveats. Minor repetition of 'in EITHER mode' and the list of codes could be tightened, but the size is justified by the complexity and the absence of an output schema.

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

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

Given no output schema, the description fully compensates by explaining return fields like spread.top_spreads_pp, compatibility_warning, compatibility_codes, temporal_alignment, fees_note, and skipped counters. It also tells the caller how to interpret nulls and warnings, making the tool safely callable and interpretable without additional documentation.

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 meaning beyond the schema by explaining that topic is a pre-mapped mode, that explicit tickers override the mapped sides, and that both modes run the same token-overlap matcher with the same disclosures.

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

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

The description begins with a specific, unambiguous statement: it computes the cross-venue spread between Kalshi and Polymarket for the same resolving question. It explains the two modes, what the tool returns, and how it differs from single-venue tools by focusing on cross-venue alignment and compatibility.

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

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

It clearly explains the two invocation modes and that both run the same matcher, plus warns that pre-mapped topics are often not tradeable. However, it never explicitly names or contrasts sibling tools such as polymarket_arbitrage or polymarket_edges, so an agent gets context but not explicit alternative routing.

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

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

Annotations already indicate readOnly, idempotent, non-destructive. Description adds scoping to identifier and that omitting key lists all. Adds value beyond annotations without contradiction.

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

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

Three sentences, front-loaded with main action, no redundant information. Efficient 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?

Covers main use cases and pairing with other tools. No output schema, but description implies return of value or list. Could be more explicit about return format, but adequate for a retrieval tool.

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

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

Schema coverage is 100% with one optional parameter. Description explains that omitting key lists all keys, adding behavioral meaning to the parameter's optionality.

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

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

The description explicitly states it retrieves a saved value or lists all keys, with specific verb+resource (retrieve/list, saved memory). Examples like user's target ticker clarify its use. It distinguishes from siblings 'remember' and 'forget'.

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

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

Clear when to use: 'look up context stored earlier...without re-deriving'. Mentions scoping and pairing with remember/forget. Could explicitly state when not to use, but guidance is sufficient.

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

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

The description describes mark_read as flagging events as read, which modifies state. This contradicts the readOnlyHint=true annotation, which explicitly promises no state modifications. The contradiction is a serious issue.

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 3-4 sentences, each adding distinct value. It is front-loaded with the core purpose and covers key behavioral aspects without 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?

For a read-oriented tool with 5 optional parameters and no output schema, the description covers the main return fields, filtering options, and the polling and alternative access behavior. It could mention pagination or limit behavior but remains 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. The description adds value by explaining that mark_read:true flags events as read so subsequent calls show only newer ones, and mentions filtering by type and since with examples. This goes 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 it pulls fired events from a subscription feed, specifying the returned fields (source, citation_uri, raw payload) and optional filters (type, since). It distinguishes itself from sibling tools like list_subscriptions or recent_changes by focusing on alert events from the subscription 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?

The description explains when to use the tool (pulling recent alerts) and mentions an alternative access method via HTTP endpoint for scripts and dashboards. It does not explicitly state when not to use it, but the context is clear enough.

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

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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false), the description discloses extensive behavioral details: it fans out to multiple sources in parallel, falls back from GDELT to GNews on rate limits or 5xx errors, notes USPTO soft-fails until reactivated due to API sunset, and specifies the return format (grouped changes with total count and citation URIs). This goes well beyond 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 and front-loaded with example queries to quickly convey intent. It is dense but every sentence adds value, covering scope, sources, parameters, fallback behavior, and return format. While comprehensive, it could be slightly more concise by using bullet points for the sources; however, it remains 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?

Given the tool has three parameters, no output schema, and moderate complexity (multiple data sources, fallback logic, soft-fail condition), the description is remarkably complete. It covers all inputs, explains the internal fan-out behavior, return structure, and edge cases like rate limiting and API sunset. No critical information is missing for correct invocation.

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

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

While the input schema already describes each parameter with 100% coverage, the description adds meaningful context: it explains that 'since' accepts ISO dates or relative shorthand like '7d', '30d', '1y', and provides typical values. It also clarifies that 'value' can be a ticker or CIK. This additional usage guidance improves semantics beyond the schema's basic 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: providing a change feed for a company in the last N days/weeks/months via a single parallel call. It lists the specific data sources (SEC EDGAR, GDELT, GNews, USPTO) and distinguishes itself from the sibling tool 'entity_profile' by specifying when to use the latter for static profiles regardless of time window.

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

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

The description provides explicit usage guidance, including example queries like 'What's new with X' and 'latest on Y'. It clearly states when not to use this tool: 'Use entity_profile instead when you want the static profile... regardless of window.' This helps the agent select the correct tool based on 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?

Adds beyond-annotation context: scoping by identifier, persistence differences (auth vs anonymous), and 24-hour retention. 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?

Reasonably concise with front-loaded purpose; every sentence adds value, though could be slightly tighter.

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 write tool with 2 params and no output schema, the description covers scope, usage, persistence, and lifecycle completely.

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

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

Schema covers 100% of parameters with descriptions; description adds naming conventions and value examples, enhancing understanding beyond schema.

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

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

Description uses a specific verb ('Save') and resource ('data...key-value pair'), and contrasts with siblings ('recall', 'forget'), making the tool's distinct purpose very clear.

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

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

Explicitly states when to use ('when you discover something worth carrying forward'), provides examples, and mentions complementary tools ('Pair with recall...forget'), giving clear usage guidance.

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

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

Annotations already declare readOnly, openWorld, and idempotent behavior, and the description adds substantial non-obvious detail: graceful degradation when GLEIF/OpenFIGI are unavailable, ambiguous matches returning figi_candidates rather than asserting an answer, unresolved identifiers being explicitly reported, and internal cascading across multiple lookup endpoints. This goes well beyond what structured 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 dense but organized: trigger phrases, supported types, and the primary use rule are front-loaded, and later caveats about ambiguity and degradation earn their place. It is long, but the length is justified by the complexity of the entity-resolution behavior.

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

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

There is no output schema, so the description carries the burden of explaining return semantics. It covers ambiguous candidates, unresolved identifiers, identifier source labeling, non-US issuer resolution, and degraded enrichment. For a complex tool with multiple entity types and cascading lookups, nothing critical is missing for selecting and invoking it correctly.

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

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

Schema description coverage is 100%, but the description still adds high-value parameter meaning: for company it clarifies CIK formatting, source coverage, and ISIN-to-LEI resolution; for value it explicitly warns to pass the entity name only, gives example formatting for bond issuers, and explains why trailing security-class words break matching. This is genuinely additive beyond the schema.

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

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

The description opens with concrete trigger phrases and a clear verb–resource mapping: resolve a user-spoken name to official identifiers. It also positions the tool against siblings by stating that other tools require these identifiers as input, so an agent can distinguish it from entity_profile or compare_entities without opening their schemas.

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

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

The description gives explicit guidance: 'Use FIRST whenever you have a name but need an ID,' plus many examples of when to invoke it. It does not explicitly enumerate exclusions versus specific alternatives like entity_profile, but the usage context is strong enough that an agent can reliably select the tool.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds valuable context: it probes each entity, ranks by score, surfaces most/least recognized, and treats the first entity as the 'subject' for narrative. No contradictions.

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

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

Three succinct sentences front-loaded with the tool's purpose, then detailing process and use case. 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?

Despite no output schema, the description explains the process (probes, ranks, returns list with metrics) and clarifies the role of the first entity. This is sufficient given the annotations and low 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%, so baseline is 3. The description adds meaning by explaining that the first entity is treated as 'subject' and that context disambiguates common names, which goes 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 it compares AI visibility across multiple entities side-by-side, using ai_visibility_check, and ranks results. It distinguishes itself from sibling tools 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?

The description provides a concrete use case ('competitive AI-marketing audits') and an example question. However, it does not explicitly state when not to use it or contrast it with alternatives like compare_entities.

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

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds valuable behavioral context beyond annotations, such as the composite nature (fans out across two services), the potential 5-30s delay on bundlephobia's first measurement, and graceful partial failures reported via sources_failed.

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 lengthy but well-structured: it opens with the composite purpose, then provides usage guidance, return summary, ecosystem scope, and error behavior. Every sentence adds value, though it could be slightly trimmed without losing essential information.

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

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

Given only two parameters, no output schema, and rich annotations, the description fully covers what the tool does, its return block (listing fields), limitations (NPM only in v1, bundlephobia latency), and partial failure behavior. No gaps remain for an agent to execute successfully.

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

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

Schema coverage is 100% with clear parameter descriptions. The description adds extra meaning by noting that scoped packages (e.g., '@types/node') are accepted for the 'package' parameter, which is not explicitly stated in the schema. This clarifies an important edge case beyond what the schema provides.

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

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

The description clearly states the tool performs a composite 'should I add this npm package to my project' check, specifying it fans out across deps.dev and bundlephobia. This makes the purpose specific and distinct from siblings like 'scan_competitor_ai_presence'.

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

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

Explicit guidance is provided: use when an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me'. The description also notes the NPM-only scope and mentions partial failure behavior, helping agents decide when to apply this tool.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. Description adds that the API can be slow, which is useful beyond annotations. No mention of errors or limits, but sufficient.

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 pack purpose, return fields, data source, auth note, and performance warning. No fluff, ideal 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?

No output schema, but description lists return fields and warns about slowness. Covers essential context for a simple search tool, though could mention pagination or errors.

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

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

Schema coverage is 100% with clear descriptions for both parameters. The description adds no extra meaning beyond the schema, meeting baseline expectations.

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 searches public preprints by title on OSF, lists return fields, and distinguishes itself from siblings by specifying the unique data source.

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?

Mentions keyless public data and API slowness, providing context for when to use. Lacks explicit alternatives or exclusions, but the niche source makes usage evident.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. The description adds useful context (keyless public data, API slow) but does not contradict annotations. The additional behavior is moderate, so a 3 is appropriate.

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 just two sentences: the first defines purpose and output, the second adds access and performance context. Every sentence is necessary and information-dense with no fluff.

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

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

For a simple search tool with two parameters and no output schema, the description covers everything essential: what it searches, how to use it (by title), what it returns (specific fields), and important context (public, slow). It 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 description coverage is 100% as both parameters have descriptions. The tool description adds that the search is by title and lists return fields, but does not add new meaning to the parameters beyond what the schema provides. Baseline 3 is correct.

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 searches public research projects by title, specifying the source (OSF), the data type (nodes), and the returned fields (id, title, description, category, creation date, tags). This is specific and distinguishes it from siblings like search_preprints or get_project.

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

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

The description mentions 'Keyless public data' indicating no authentication needed, and warns that the API can be slow. It implicitly distinguishes from tools like get_project (by ID) or search_preprints. However, it does not explicitly state when to use or when not to use this tool versus 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?

Discloses embedding model (BGE-base-en), chunking strategy (500-char overlapping windows), cap of 200K chars with truncation and flag, and output details (character offsets, similarity scores). This adds value beyond the annotations which already indicate safe, idempotent read.

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 four sentences: purpose, examples, use-case with pairing, and technical details. Every sentence adds value, no redundancy. Front-loaded with key action and resource.

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

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

Despite lacking an output schema, the description fully explains return values (top-N passages, offsets, scores) and edge cases (truncation). Pairs well with sibling tools and covers all critical aspects for invoking the tool.

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

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

Schema covers all 3 parameters with descriptions. The description adds example queries and notes the default limit of 5, plus clarifies the cap in the text parameter. While helpful, the schema already does most of the semantic work.

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

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

Clearly states it performs semantic search inside a fetched record, with specific examples like SEC 10-K and article. Differentiates from siblings by mentioning pairing with ask_pipeworx_grounded and contrasting with cramming large records into prompts.

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

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

Explicitly recommends using when the record is too big for the prompt and pairs with ask_pipeworx_grounded. Does not explicitly list when not to use, but context implies it is for large texts. Could be stronger with more explicit exclusions.

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

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

Annotations indicate non-read-only, idempotent, and non-destructive. The description adds behavioral context: delivery channel details, SMS rate limits (10/day), webhook auto-disable after 10 failures, and the one-time return of webhook secret. It does not explicitly mention idempotency but is consistent with the annotation.

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

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

The description is fairly long but concise, with each sentence adding value. It front-loads the purpose and outcome. Could benefit from bullet points or shorter sentences, but overall efficient.

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

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

The description covers all aspects for a subscription creation tool: purpose, prerequisites, types, parameters, delivery options, limitations (SMS cap, webhook auto-disable), and cross-references to related tools/endpoints. No output schema is present, but the return value is stated.

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

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

Schema coverage is 100%, and the description adds extensive meaning beyond schema descriptions: type examples, detailed parameter structures for each type, delivery channel options with caveats and requirements (e.g., phone verification, 10/day cap, webhook signing).

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 'Create' and the resource 'proactive monitoring subscription to a live-data event stream', and specifies the return value 'Returns the new subscription id'. This distinguishes it 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 including prerequisites ('Requires a Pipeworx OAuth account'), supported types with examples, and delivery channels. It does not explicitly state when not to use or suggest alternatives, but the context is sufficient for an agent to decide.

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

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

Annotations (readOnlyHint, openWorldHint, idempotentHint) are all consistent. The description adds valuable context: the tool returns example questions with tool+argument shapes drawn from the live catalog, and default behavior when no arguments are passed.

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

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

The description is a single paragraph front-loaded with synonyms, then explains purpose and usage. It's moderately sized and every sentence adds value, though could be slightly more compact.

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 high schema coverage, good annotations, and no output schema, the description fully explains what the tool returns and when to use it. It covers the purpose, usage, and output format comprehensively.

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 covers 100% with clear enum of topics. Description adds the nuance that omitting the topic gives a full cross-category spread, which is a useful behavioral detail.

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

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

The description clearly states the tool is an onboarding entry point that returns category-bucketed example questions with exact tool+argument shapes. It distinguishes from siblings like ask_pipeworx and other meta-tools by specifying it's for getting started and learning how to call 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 says 'Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools'. It also provides argument guidance: call with no arguments for full spread, or pass a topic to focus.

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

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

Annotations already indicate non-destructive and idempotent behavior. The description adds critical context: ownership enforcement (unauthorized calls fail) and soft-delete behavior ('row is deactivated not deleted'), plus why history remains available. No contradiction with annotations.

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

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

Two sentences, no wasted words. The first sentence states the core action, the second explains ownership and effects. Front-loaded and efficient.

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

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

The description fully covers the tool's purpose, constraints, and side effects. Given a single parameter, no output schema, and clear annotations, nothing is missing. It explains both the immediate and downstream impacts.

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

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

Schema coverage is 100% with a clear description for the 'id' parameter. The description adds value by tying the id to the 'subscribe' tool ('returned by subscribe'), which aids tracking and usage.

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

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

The description clearly states 'Cancel a subscription by id' with a specific verb and resource. It distinguishes from siblings like 'subscribe' and 'list_subscriptions' by specifying cancellation. The ownership enforcement further clarifies the scope.

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

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

The description explains when to use by id and enforces ownership, but does not explicitly mention when not to use or provide alternative tool names. However, sibling tools provide context, and the description covers key usage constraints.

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

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

Beyond the readOnly/idempotent annotations, the description discloses crucial behavioral nuances: the exact meaning of could_not_verify (pipeline failure, not evidence) vs. unsupported (no source), the routing logic, and the percent-delta math for financial claims. This is critical for callers to interpret results correctly and is far richer than 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 dense but well-structured: trigger phrases, usage, routing, return values, error semantics, and efficiency note all flow logically. Every sentence contributes unique information without 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?

For a high-complexity claim verification tool with no output schema, the description thoroughly covers return types, verdict semantics, error handling, routing logic, and intended use case. It is self-sufficient for an agent to select and invoke the tool safely and interpret results correctly.

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

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

Schema description coverage is 100% with detailed inline documentation for both claim and tolerance_pct, including default and allowed ranges. The tool description itself adds no parameter-specific guidance beyond mentioning 'exact percent-delta math,' so the baseline of 3 applies.

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

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

Description opens with concrete trigger phrases and explicitly states 'natural-language claim verification against authoritative sources,' making the tool's purpose unambiguous. It goes further by describing the two routing pipelines (SEC EDGAR for financial claims, grounded pipeline otherwise) and returns a specific verdict set, clearly distinguishing it from sibling research tools.

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

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

Explicitly instructs 'Use whenever the agent needs to check whether something a user said is factually correct' and provides natural-language call patterns. It also explains that the tool replaces 4–6 sequential calls, positioning it as the streamlined alternative for this task.

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