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

Annotations only declare readOnlyHint and destructiveHint=false, yet the description adds real behavioral context: the forensic repro criteria that define flaky, the exact per-entry fields returned, and the important caveat that flaky tests are never skipped or quarantined (information only). It does not cover auth needs, rate limits, ordering, or pagination, keeping it off 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?

The purpose is front-loaded in the first sentence, and the dense definitional material about the repro and entry fields is mostly load-bearing because 'flaky' would otherwise be ambiguous. The closing sentence about retry and merge-gate excusal is somewhat tangential to a listing tool and stretches the length.

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 enumeration of returned fields (test, file, state, label, variable, repro command, owner, expiry, issue, flip rate, evidence runs) is exactly what an agent needs, and the state semantics including 'unexplained = NOT flaky' prevent misreading. Gaps remain around pagination, ordering, and the owner/repo parameter expectations.

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 coverage is only 50% — limit and window_days are described in the schema, but owner and repo are bare strings with no format guidance. The description compensates by naming none of the four parameters: it never links window_days to the flip-evidence window or explains limit/pagination, so the undocumented half stays unexplained.

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 first sentence gives a specific verb and resource ('List a repository's flaky tests') and the rest of the description sharply scopes what counts as flaky, which separates it from generic failure tools like explain_failure or get_workflow_logs. It never names an alternative sibling explicitly, so it stops short of the top mark.

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?

Usage is implied rather than stated: the descriptions of 'unexplained = NOT flaky', the single targeted retry, and the merge-gate excuse suggest this is the tool to consult when judging whether a CI failure is trustworthy. There is no explicit 'use this when / not when' or named alternative (e.g. explain_failure for root-cause analysis).

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