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

With readOnlyHint and destructiveHint already declaring a safe read, the description still earns credit by disclosing that part of the result comes from an AI model, that a guard drops any figure, name or tool not present in the user's text, and that the rule-based portion still returns with an explanation in ai.message when the model is unavailable. It does not state explicitly that repeated calls may produce different rewrites, which is the remaining gap for a non-idempotent tool.

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 trigger is front-loaded and each sentence carries information, but the parenthetical listing 'Gemma 4, with Llama 3.3 70B as a backup, on Cloudflare Workers AI' is implementation trivia that does not change how the agent calls the tool. Trimming that clause would tighten an otherwise dense but well-structured description.

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?

There is no output schema, and the description compensates by naming the shape of the result (score, verdict, fixes, up to three rewrites, ask_user, ai.message) plus the degradation path. For a three-parameter read-only tool with annotations covering safety, nothing needed to invoke it correctly is missing.

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%, so role, company and bullet are already documented in the schema, and the description adds no syntax or usage detail for role/company. The mention of ask_user and 'keep every fact as given' refers to response fields and copy constraints rather than to input parameters, so the baseline of 3 is appropriate.

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 opening sentence names a specific verb and resource ('one resume bullet rewritten or made stronger') and the second sentence clarifies it also scores the bullet the way check_bullets does. An agent can distinguish it from check_bullets (checks only) and from multi-bullet tools 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?

The trigger condition ('when the user wants one resume bullet rewritten') is stated up front, and the relationship to check_bullets is made explicit by describing the shared check step. It stops short of an explicit exclusion such as 'for multiple bullets use check_resume', so the routing is clear but not fully closed.

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