screen_candidate

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

No annotations are supplied, so the description carries the full disclosure burden, and it does state 'Read-only' and that everything is returned 'in one call' (no follow-up calls required). It does not cover permission requirements or any rate/volume limits, but the key safety trait and the single-call behavior are disclosed.

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 identity of the tool and its read-only nature are front-loaded in the first two sentences, and the return-value list is compact. The middle 'Users say...' sentence is the softest part but still earns its place by supplying recognition triggers.

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 a 100% covered single required parameter and an output schema present, the description need not explain return shapes, yet it still previews the payload so the agent knows this replaces several narrower calls. The only real gap is not positioning it against the adjacent single-purpose readers.

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's own description already contains the search_candidates_by_name -> list_applications resolution chain, so the description's restatement adds no meaning beyond the structured field. Baseline 3 applies when the schema does the heavy lifting on a single-parameter tool.

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 ('Full screening package for one candidate application') and then enumerates exactly what the package contains (profile, resume text, location, screening answers, job description, application history). That enumeration distinguishes it from narrow siblings like get_application, get_candidate, and read_candidate_resume without the agent opening a schema.

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 concrete invocation triggers ('screen Sarah for the Backend role', 'give me the full picture') and an explicit ID-resolution path: search_candidates_by_name -> list_applications(candidate_id=...) -> match the application to the job name. What is missing is an explicit when-not-to-use, e.g. that get_application or read_candidate_resume should be preferred when only one piece of data is needed.

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