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

Annotations already declare a safe read, and the description adds substantial behavior beyond them: the result is plain text, and specific fields (surname, contact details, links, employer names, city, referees) are stripped. That redaction disclosure matters because an agent might otherwise expect identifying details in the output, and the availability gating is disclosed too.

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?

One sentence that front-loads the return value, then the redaction set, then the availability condition. Nothing is padding; every clause adds usable 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?

For a one-parameter read tool with no output schema, the description covers what is returned, what is withheld, and when the tool is usable. It leaves minor gaps: what happens (error vs empty) when resumeAvailable is false, and whether long resumes are truncated or paginated.

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 single parameter is self-documenting as 'candidateRef from search_candidates'. The description reinforces that provenance but adds no format or validation detail 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?

States a specific verb and resource ('Returns the resume of a candidate') plus the exact output form ('as text') and ties the identifier back to search_candidates. This clearly distinguishes it from search_candidates, get_request_status, and request_intro.

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?

Establishes the prerequisite workflow (obtain the ref from search_candidates) and a gating condition ('Available when the profile says resumeAvailable'). It stops short of stating what to do when resumeAvailable is false or which alternative to fall back to, so it is clear context rather than a full when/when-not rule set.

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