Cerulean Jobs

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

Beyond the readOnlyHint, idempotentHint, and non-destructive annotations, the description discloses that unknown or closed listings produce an error and that the tool returns the full listing as text with URL and structured details. These are non-obvious behavioral details useful for agent invocation, and nothing contradicts the annotations.

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

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

The description is front-loaded with the exact usage trigger, then states the return payload, the non-search behavior, and the error condition. Every sentence earns its place; no filler or redundant restating of the title.

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 rich parameter schema, output schema, and annotation coverage, the description covers all remaining decision-relevant context: when to use it, what it returns, what it does not do, and how errors behave. The agent has enough to invoke 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%, and the schema already explains id and locale in detail including locale-specific site mappings. The description reinforces that id can be a URL, but it does not meaningfully add beyond the schema, 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 states a specific verb and resource: fetching one specific Cerulean listing when its id or URL is known, and returns it in full. It explicitly distinguishes itself from searching ('It does not search.'), which separates it from the sibling tools search and find_similar_jobs.

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 trigger is explicit: use when someone asks about one specific listing with a known id or URL. It also gives an exclusion ('It does not search.') and an error condition for unknown or closed listings. It does not explicitly name search or find_similar_jobs as alternatives, but the contrast is clear enough.

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

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

Annotations already cover readOnly, idempotent, and destructive hints, so the description's main contribution is the error behavior: it returns an error for unknown listings or missing similarity data instead of unrelated results. This adds useful behavioral context beyond the annotations, though it doesn't detail output format (covered by the output 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?

The description is two sentences with no fluff. It front-loads the core purpose and usage, then adds the error behavior, which is essential for the agent to set expectations. Every sentence earns its place.

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

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

Given the output schema exists and the input schema fully documents all 6 parameters, the description provides sufficient context for correct invocation: it clarifies the input type (id), the error case, and the general behavior. Nothing critical is missing for an agent to use the tool correctly.

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

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

Schema coverage is 100%, so all parameters are already documented with detailed descriptions (e.g., id, limit, locale, offset, country, location). The description adds minimal extra meaning beyond what the schema provides, mainly reinforcing that the id is a listing id, not keywords. This meets the baseline for 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 clearly states the tool's purpose: finding similar jobs based on a specific listing's id, distinguishing it from keyword-based search. It uses a specific verb ('find') and resource ('similar jobs'), and explicitly notes it takes an id, not keywords, which separates it from the sibling 'search' tool.

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

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

It gives explicit when-to-use context ('when someone wants more roles like one specific Cerulean listing') and describes error behavior for invalid input. It doesn't explicitly name alternatives like 'fetch' or 'search', but the 'not keywords' phrasing implies when not to use it, making the guidance clear enough.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, but the description adds rich behavioral context beyond that: data freshness ('read from the houses' own career sites every four hours, and closed roles drop out'), query interpretation ('a brand, place, country or employment type it names is applied as that filter'), result pagination ('Returns one page of listings... plus total'), and locale handling (site mapping and fallback behavior). These are not derivable from annotations.

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

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

Though long, every sentence earns its place. The description front-loads the primary purpose, then systematically covers filtering, query parsing, freshness, pagination, and locale behavior. It is organized logically and free of filler.

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

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

Given the tool's complexity (12 parameters, multiple enums, locale mapping) and the presence of an output schema, the description is comprehensive. It explains the interaction of filters, query semantics, freshness, pagination, and locale without needing to describe the return structure (covered by output schema). Nothing an agent needs to call it correctly is missing.

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

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

Schema coverage is 100%, giving a baseline of 3, but the description substantially enriches parameter meaning. For query it explains empty-value browsing, sentence parsing, and filter inference; for locale it details BCP 47 usage, site mapping, and non-filtering semantics; for posted_within_days it clarifies the counting basis. It also clarifies that brand, place, employment type, etc. combine, which the schema does not state.

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

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

The description explicitly states the tool's function: 'find, browse, count or compare open roles at luxury houses and brands'. It names the resource (job listings) and the scope (luxury houses, newest openings included). Though it does not name sibling tools, the verb set and 'open roles' make it distinct from fetch (retrieve one) and find_similar_jobs (similarity matching).

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 opens with a clear when-to-use directive: 'Use this when someone wants to find, browse, count or compare open roles'. It explains filter combinations and query behavior. However, it does not explicitly mention when to prefer sibling tools (fetch or find_similar_jobs) or when not to use this tool, so it stops short of full exclusion guidance.

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