Resume Proposal

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the agent knows it mutates without destroying. The description adds genuinely useful context beyond annotations: it releases a daily-cap reservation and is refused for submission_uncertain proposals. It does not explain permissions or the full effect of the state change.

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 terse sentences, each earning its place: the action, the side effect, and the refusal condition. Fully front-loaded with zero filler.

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 mutation with annotations covering the safety profile and no output schema, the state transition, side effect, and refusal condition are enough to avoid misuse. However, it omits the parameter's meaning and how to reach the needs_human state, leaving meaningful gaps.

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?

With one required parameter at 0% schema coverage, the description carries the burden of documenting proposal_id but never mentions it, its format, or where to obtain it. It only implicitly constrains which proposals are eligible. Baseline 3 is the best fit.

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 state transition: it moves a needs_human proposal to pending_review. A reader can distinguish it from get_proposal or request_decision. However, it does not say what 'preparation' is or which sibling performs it, so scope is partly implied.

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 description implies usage by describing the state transition but never states when to call this versus alternatives like request_decision or record_decision. It also gives no prerequisites, only a refusal condition.

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