Judge Resume Bullets

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

Beyond the annotations (which only say non-read-only, non-destructive, non-idempotent), the description discloses the acceptance rules — analogue/direct require a verbatim ≥3-word quote or the level is downgraded to adjacent, measure questions survive only if the target is in the bullet's own words — plus rejection of non-pending ids, storage under the client's name, and the 409 conflict condition.

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?

Every sentence earns its place and the core effect leads, but the prose is packed into long run-on sentences (the opening sentence alone carries two clauses plus a parenthetical), which makes it denser to parse than necessary.

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, yet the description explains the return value — the rebuilt report with the same fields as run_health_check plus accepted [{id, level as stored}] and rejected [{id, reason}] — and covers error behavior, so an agent has everything needed to call it and interpret the result.

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 0%, so the description must carry the load, and it does: kind is 'base' or 'application', key is the slug or application id, and classifications is the list from run_health_check's judging.prompt output shape with one entry per pending id and enumerated level values (direct, analogue, adjacent, implied, unaddressed).

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?

It states a specific verb and resource — stores evaluations of pending resume bullets, then rebuilds the health report — and situates it against the sibling run_health_check by naming the exact condition under which the judging is delegated to the client. An agent can distinguish it from run_health_check and get_health_report 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 when-to-use condition is explicit: it applies while Maestro's own model does not judge (no model key set, or the agent app writes), and the exclusion is spelled out too — a 409 fires while Maestro's own model judges. It also points the caller at judging.prompt from run_health_check as the source of the input shape.

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