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

Annotations give only readOnlyHint and openWorldHint, so the description carries most of the behavioral burden. It discloses significant non-obvious traits: scores are stripped from fields and scrubbed from note prose, judge labels are stable but deliberately carry no ranking, remote-evidence-audit entries are labelled, phase gating differs by role, and required scope includes a team seat. These go well beyond the annotations without contradicting them.

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 description is long but every sentence earns its place: it covers redaction behavior, judge-label semantics, organizational audit labels, phase/role gating, return shape, and required scope. It is highly informative and mostly front-loaded. The minor ding is that it restates 'Args: { eid? }' and 'Required scope' near the end without adding meaning, so it is not maximally tight.

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?

With no output schema, the description supplies the return shape and field semantics, which is excellent for a one-param, read-only tool. It also gives role- and phase-specific access rules and clearly separates this call from ic_hack_results. The one meaningful gap is the missing eid semantics and default behavior, which keeps it from being fully complete.

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?

The input schema gives only eid: string, maxLength 64, and schema description coverage is 0%, so the description must explain what eid means and what happens if omitted. It merely restates 'Args: { eid? }', adding no semantics beyond the schema. An agent is left guessing whether eid is an event id, whether omission selects a current event, and what values are valid.

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 description opens with a clear, specific verb-and-resource statement: it returns the written feedback judges left on the caller's own team's submission, with scores removed. It further differentiates itself from siblings by explicitly stating that scores live in ic_hack_results and that comments are scrubbed from prose, so an agent can immediately tell this is the qualitative feedback tool, not the scoring or admin feedback tool.

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 gives concrete when-to-use/access conditions: teams are gated to RESULTS, judges and organizers can preview from LOCKED onward, and a team seat is required. It also names the alternative explicitly ('Scores themselves stay in ic_hack_results, which is a separate call'), which routes an agent away from this call when scores are needed.

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