Update Candidate

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, and the description enriches this by explaining the exact mutation scope: updating the candidate and optionally creating up to 10 work history and 10 education history rows. It discloses partial-success behavior ('partial-success details for history operations'), resume file format constraints, and that file-type custom fields accept only a direct download URL. No contradiction with annotations 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 four sentences, front-loaded with the primary purpose. Each subsequent sentence earns its place: requirements, resolver guidance, file format constraints, and return summary. It is concise relative to the 44-parameter schema, though it is dense and could be slightly restructured for readability. No filler or repetition of schema-only 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 tool with 44 parameters, nested arrays, and no output schema content in the description, the description covers the essential context: target resource, required/conditional fields, how to resolve IDs, file format restrictions, and return behavior. It does not explicitly state whether unspecified fields are left unchanged or reset, but the up to 10 rows and partial-success details suggest a reasonable update semantics. Given the output schema exists and annotations are present, the 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?

With 100% schema description coverage, the baseline is 3, but the description adds meaningful semantics beyond the schema. It maps logical parameters to resolver tools ('currency_id with list_currencies', 'language_skills with list_languages_and_proficiencies'), clarifies the resume field accepts base64 or URL, and explains that file-type custom fields only accept a direct download URL. It also introduces the conditional requirement that at least one of first_name or last_name must be provided, which is not encoded in the schema's required list.

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 a specific verb ('Updates'), resource ('one existing Recruit CRM candidate'), and identifier ('by candidate_slug'), distinguishing it from sibling tools like create_candidate and search_candidates. It also names the exact operation scope (update plus optional history creation), leaving no ambiguity about what the tool does.

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 on resolving foreign keys ('Resolve user IDs with list_users, currency_id with list_currencies...'), which helps agents prepare correct parameter values. It also clearly implies the tool is for updating an existing candidate (not creating one), but it does not explicitly name alternative tools or state when not to use it. The conditional requirement 'at least one of first_name or last_name' adds useful usage context.

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