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

Annotations mark this as a non-read-only, idempotent, non-destructive write, and the description adds context the annotations cannot: a later report for the same step replaces the earlier verdict (consistent with idempotentHint), credentials must come from the plan response, and the data feeds future rankings. It stops short of stating failure modes, such as what happens with an expired or invalid feedbackToken.

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 dense sentences, front-loaded with a useful '[free]' cost marker and the core verb, with the credential requirement ahead of the replace-semantics note. Every sentence carries information; only the parenthetical field list is mildly compressed.

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 state-mutating reporting tool with an output schema, this is nearly complete: it explains provenance of the identifying parameters, the replace semantics, and the downstream use. The only gap is guidance on invalid or expired tokens and confirmation of what the write affects.

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 only 14%, so the description has to compensate, and it does for most fields: it names decisionId and feedbackToken and explains where they come from, and covers outcome, quality (1-5) and latency. Only the step index is left implicit, inferred from its name and the minimum-1 schema constraint.

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 — report the outcome of one step of a decide.plan decision — and enumerates the accepted fields (success/failure, optional 1-5 quality and latency). An agent can distinguish this feedback call from the sibling decide.plan and decide.execute tools without opening the 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?

Establishes the calling context clearly: it is used after decide.plan, requires the decisionId and feedbackToken that call returned, and that one verdict applies per step. It does not explicitly name alternatives or say when not to report, but the sequencing is unambiguous.

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