Check corpus integrity

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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses that the tool is deterministic, never repairs records, and only covers private records when the server runs with --include-private. It also clarifies the error/warning levels and recovery text, adding significant behavioral context not captured by annotations.

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 packs a high amount of useful information into two sentences, front-loaded with the primary use case. Every phrase adds value, such as the error/warning distinction and the privacy caveat, with no wasted words.

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?

Given the tool's simplicity (no params, no output schema), the description covers all relevant aspects: purpose, trigger conditions, behavior, and alternatives. It even mentions the --include-private flag and recovery text, making it a complete guide for the agent.

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 tool has zero parameters, so the schema is empty. The description cannot add parameter semantics beyond the schema; baseline 4 applies since no parameters need explanation.

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 clearly states the tool's function: it reports broken supersedes and replyTo references, self-references, supersedes cycles, and competing forks. It also distinguishes itself from run_doctor, which handles directory, secret, and audit-log checks, providing clear differentiation from siblings.

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?

Explicitly advises use after imports or before trusting a supersedes or reply chain, and directs users to run_doctor for alternative checks. This gives both when and when-not guidance, fully satisfying the criterion.

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