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

Annotations already declare destructiveHint=true and idempotentHint=false; the description softens this with 'the master never changes' and adds meaningful invariants (no invented facts, no dropped content, versioning semantics). There is mild tension between destructiveHint=true and 'master never changes', but saving a new version is plausibly non-destructive to the master, so this reads as clarification rather than contradiction. What it never covers — what happens to the prior tailored version, storage limits, or failure/rollback behavior — is left unexplained.

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, front-loaded with the core action and its scoping rule before the content and questioning rules. Dense and mostly earned, though the run-on 'Wording the resume supports goes in; a new fact does not, nothing is dropped' is telegraphic enough to risk misparsing.

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 7-parameter, deeply nested write tool with no output schema and 57% schema coverage, the description covers the workflow but leaves key gaps: it references a questions[] array that does not appear in this schema without saying which sibling produces it, and it never indicates what a successful save returns (version id? confirmation?) for the caller to hand back.

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%, so the schema carries most of the load and the baseline is 3. The description does add genuine meaning for two params: the exact userStatedFacts shape ({questionId, text}) and the semantic rule for content (paraphrase only). It says nothing about resumeId, jobDescription, company, or targetTitle beyond what the schema already states.

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 — 'Saves a version for a job ad' — and immediately scopes it with 'the master never changes', which distinguishes it from update_resume (mutates master) and create_resume (new resume). It doesn't name those siblings explicitly, so an agent must infer the boundary, but the intent is legible.

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?

Gives real operating constraints: only wording the resume already supports goes in, no new facts, nothing dropped. It also prescribes the question-relay protocol (pass questions[] verbatim, never answer them yourself) and the answer channel (userStatedFacts). What's missing is an explicit statement of when to pick this over update_resume/score_resume.

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