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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description goes well beyond them: input limits (30 bullets, 600 chars each), skip-and-report semantics for blank items, the scoring model (score + verdict + fixes), the stable problem-code taxonomy, and a pinned rules version. That is substantive behavioral context an agent could not derive from the structured fields.

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 routing condition is front-loaded and nearly every sentence carries new information (limits, skip behavior, scoring, codes, version). The middle sentence is a dense comma-list of problem categories that is slightly harder to parse than a bulleted enumeration would be, but nothing is redundant.

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 two-parameter, non-destructive check tool with no output schema, the description covers inputs, limits, skip handling, scoring model, and the code taxonomy. The remaining gap is the exact response shape (per-bullet objects, whether an aggregate score is returned), which the agent must infer from the check_resume analogy.

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 the baseline is 3, but the description adds real meaning beyond the schema: it explains that blank items are skipped and reported by index, which is non-obvious input-handling behavior. It says nothing about the language parameter (the English-rule skip is only in the schema), which keeps it from a 5.

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 first sentence names a specific verb and resource ("resume bullet points checked") and immediately scopes it against the alternative of sending a whole resume. Combined with the explicit reference to check_resume scoring, an agent can distinguish this from check_resume, improve_bullet, and the LinkedIn check siblings without 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?

"Use this when the user wants a few resume bullet points checked without sending the whole resume" gives a clear selection condition, and "Scored as check_resume scores bullets" positions it relative to the full-resume tool. It does not explicitly name improve_bullet as the alternative when the user wants rewrites rather than checks, so one obvious routing decision is left to inference.

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