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

Annotations cover idempotency, non-destructiveness, and read/write status; the description nonetheless adds real value by disclosing upsert behavior ('a later report replaces it') and the downstream effect ('feed tool reliability in future rankings'). It omits permission/token-expiry behavior, keeping it short of a 5.

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 tight sentences, front-loaded with the [free] cost marker and the core action, then prerequisites, then behavioral notes. No 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?

An output schema exists so return values need no explanation. Combined with annotations and the description, an agent has enough to call this correctly; only edge cases like token expiry or what happens to prior reports after replacement are unaddressed.

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 must compensate, and it does for the core params: it names decisionId, feedbackToken (and where they come from), step, outcome, plus 1-5 quality and latency. Only toolId goes unmentioned in prose, though the schema itself describes it well.

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 (Report) and resource (one step of a decide.plan decision), and its outcome semantics (success/failure). An agent can distinguish it from decide.plan and decide.execute immediately because it explicitly describes post-step reporting.

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?

Clear context: use after a decide.plan step, requires the decisionId and feedbackToken that decide.plan returned, one verdict per step, later report replaces earlier. No explicit alternatives are named, but with only two related siblings the routing is obvious and the prerequisite is spelled out.

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