RentSeek Evidence

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

Annotations already indicate readOnlyHint=true, so the description adds value by disclosing the credit cost and a disclaimer ('not investment advice'). No contradictions, and the extra context about auth requirements further aids an agent in understanding behavioral constraints beyond safety.

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

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

Two sentences: first clearly states what the tool returns, second adds essential context (auth, cost, disclaimer). No unnecessary words, but could be more structured with bullet points or clearer separation of concerns.

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 lists five returned fields but does not specify their format or structure (no output schema). Given the tool's simplicity (one param), this is moderate but not fully complete – an agent might need to infer the response shape. For a tool without output schema, more detail on the output structure would improve completeness.

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

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

The input schema has 0% description coverage; the description compensates minimally by noting that the claim ID is a RentSeek `clm_...` ID, adding format context. However, it does not elaborate on the parameter's purpose or constraints beyond the schema's minLength, leaving significant gap for the agent.

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 returns specific fields (value, filing source, etc.) for a RentSeek claim ID, using a specific verb 'Returns'. The resource is well-defined as 'claim evidence' and is distinct from sibling tools like get_company_dossier or list_available_tickers.

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

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

Description mentions required authentication (OAuth or X-API-KEY) and cost (1 credit), which provides context but does not explicitly guide when to use this tool vs alternatives. Implicitly, it is for retrieving claim evidence by ID, but no when-not-to-use or sibling comparisons.

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. Description adds that it costs 3 credits, requires OAuth or X-API-KEY, and that results are filing evidence not investment advice. No contradictions.

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

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

Two sentences, front-loaded with purpose, no fluff. Every sentence adds 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?

No output schema, but description lists key contents and qualifies the result as filing evidence. Could elaborate on return structure or pagination, but it's reasonably complete for a dossier 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 description coverage is 0%, so description must compensate. It mentions 'ticker' (implied), 'optional full or compact format', and 'field projection'. It lists some fields (e.g., executives, compensation_history) but does not fully enumerate all enum values from the schema (e.g., company, sources, limitations are missing). Adds partial meaning.

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

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

Clearly states the tool returns a sourced company dossier for a ticker, listing specific contents like executives, compensation, pay ratio, etc. Distinguishes from sibling tools like get_executive_compensation (narrower) or get_claim_evidence (specific to claims).

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

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

Specifies authentication requirements and credit cost, but does not explicitly state when to use this tool vs siblings or when not to use it. Lacks explicit alternatives or exclusions.

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

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

The description discloses credit cost differences based on filters, authentication requirements, and that the result is filing data, not investment advice. The readOnlyHint annotation is consistent with the read nature; description adds value beyond annotations by explaining costs and disclaimers.

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

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

The description is relatively concise for the amount of information conveyed. It front-loads the core purpose and then adds usage details. Every sentence adds value, though could be slightly trimmed without losing meaning.

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

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

Given no output schema, the description mentions pay components, totals, and filing source URLs, giving a reasonable idea of the response. However, it does not specify the exact structure or field names, which would be helpful for a tool with 7 parameters and no output schema.

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

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

Schema coverage is 57% (4/7 params described). The description adds context about parameter combinations (e.g., 'Omit all fiscal-year filters to get the latest year'), which helps, but does not detail individual params beyond what schema provides. At moderate coverage, description partially compensates but not fully.

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

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

The description clearly states it returns named-executive compensation rows for a company by ticker/CIK with fiscal-year filters and pay components. It explicitly excludes pay ratio, pay-versus-performance, and dossiers, distinguishing it from sibling tools like get_company_dossier.

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 specific guidance on when to use: latest-FY requests cost 0 credits and no auth, while historical/range/multi-FY require OAuth/X-API-KEY and cost 1 credit. It notes exclusions (pay ratio, etc.), but does not directly compare to siblings for when to choose this 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?

Beyond the annotations (readOnlyHint=true, openWorldHint=false), the description clarifies that the result contains only availability, not compensation values, and adds a disclaimer that it is not investment advice. This provides useful context 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?

Three sentences: purpose, cost/auth context, and scope disclaimer. All earn their place, no redundant text. Front-loaded with the core function.

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

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

Given no output schema and 0 parameters, the description adequately explains the returned data (tickers) and its limitation (no compensation values). It could mention ordering or if the list is exhaustive, but the current version is mostly complete for a simple listing tool.

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

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

The tool has zero parameters and schema description coverage is 100% (trivially). The description does not need to add parameter meaning; its mention of 'no authentication' is behavioral, not parameter-related. Baseline 4 for 0 parameters is appropriate.

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

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

The description clearly states the tool returns ticker symbols for companies with published RentSeek executive-compensation data. It uses a specific verb ('Returns') and a well-defined resource, distinguishing it from sibling tools like get_company_dossier or get_executive_compensation.

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 notes that no authentication is required and costs 0 credits, implying low friction for use, but does not explicitly specify when to use this tool versus alternatives (e.g., for initial ticker discovery before fetching compensation). No exclusions or when-not-to-use guidance is provided.

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

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

The description adds behavioral context beyond the readOnlyHint and openWorldHint annotations: it requires OAuth or X-API-KEY, costs 2 credits per page, and notes the result is filing evidence, not investment advice. No contradiction with annotations.

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

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

The description is four sentences long and front-loads the main purpose. Most sentences are informative, though the disclaimer about investment advice is marginally necessary. 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?

Given no output schema, the description does not detail the structure of returned events (e.g., fields included). It mentions pagination and classification but omits the exact response format. For a tool with 7 parameters, more completeness on output would be helpful.

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

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

With 100% schema description coverage, the baseline is 3. The description adds value by explaining concepts like 'inclusive date or timestamp', 'opaque next_cursor', and the 1-50 ticker limit, enhancing clarity beyond the schema alone.

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

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

The description clearly states the tool returns classified executive-compensation disclosure changes for 1-50 tickers since an inclusive date. It specifies what is included (changes, not snapshots or full history) and distinguishes from sibling tools by focusing on material changes.

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 authentication requirements (OAuth or X-API-KEY) and cost (2 credits per page). It also states it does not include current snapshots or full historical rows, providing some guidance when not to use it. However, it does not explicitly compare to sibling tools like get_executive_compensation.

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 leave real gaps (no auth, rate-limit, or idempotency detail), and the description fills them: authentication not required, rate-limited per email and per client, 0-credit cost, and the crucial fact that no key exists until the owner clicks the sign-in link. This is behavior an agent cannot infer from readOnlyHint/openWorldHint.

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?

Front-loaded with purpose and mechanism, and nearly every sentence carries operational value (token flow, auth, rate limits, cost). The closing 'It is not investment advice' is boilerplate noise that doesn't help invocation, keeping it from a 5.

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 correctly covers return values (a `request_token` on first call, the key on the confirmed repeat call), plus auth, rate limits, and cost. An agent has everything needed to call this correctly across both phases.

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 both parameters are documented; the description adds sequencing semantics the schema cannot express — that `request_token` comes from the first call and is only sent after owner confirmation, and that `email` is the key owner. That is genuine added meaning above the baseline.

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

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

Names a specific verb and resource (request a RentSeek API key) and immediately scopes the outcome (100 credits, free). The two-phase mechanism (sign-in link, no key until clicked, token-then-key) makes it unmistakably distinct from the read-only siblings like get_company_dossier and list_available_tickers.

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?

Spells out the exact call sequence: first call with `email` returns a `request_token`; repeat call with `email` + `request_token` after the owner confirms returns the key once. This is effectively when-to-use guidance. It doesn't discuss explicit alternatives, but there is no competing sibling for key issuance.

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

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

With annotations only declaring readOnlyHint=false, destructiveHint=false, openWorldHint=false, the description carries real extra value: it specifies rejection-without-persist for secret-bearing, oversize, or malformed payloads, optional authentication with anonymous rate limiting, zero credit cost, and that the result is a receipt rather than analysis. These operational traits are not derivable from the annotations or schema.

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?

Roughly five sentences, each carrying distinct information (payload shape, return value, triage ownership, rejection policy, auth/cost). Front-loaded with the core action, though the trailing 'not investment advice' clause is marginally tangential.

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 mutation tool with nested params and an output schema, everything an agent needs is present: payload shape, return value, auth/rate-limit behavior, failure modes, cost, and downstream disposition. Return-value details are rightly delegated to the existing output schema.

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

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

Schema description coverage is 0% across 8 params, so the description must compensate — and it does, enumerating category, message, and every optional field (URL, route, tool, request ID, trace ID, reproducible context). It stops short of clarifying per-field constraints such as message length or the context sub-object's ticker/fiscal_year/executive_id fields, so it is strong but not exhaustive.

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

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

States a specific verb ('Accepts') and resource ('structured product-feedback report'), plus an enumerable payload (category, message, optional URL/route/tool/request ID/trace ID/context) and the returned artifact (opaque report ID). This cleanly separates it from the read-only siblings (get_claim_evidence, get_company_dossier, etc.) without needing their schemas.

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

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

Usage context is clear: this is the submission path for product feedback, costs 0 credits, and disposition is owned by human triage. It does not explicitly name a when-not or an alternative sibling, but none exists for a write/feedback tool in this toolset, so the guidance is adequate rather than exhaustive.

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