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

Annotations only mark this as a destructive, open-world, idempotent write; the description carries far more: the operation is asynchronous (RUNNING can take half an hour), the outcome is surfaced later on get_issue's fix block, retries only re-push the pull request rather than re-doing work, and nothing is ever merged. The full status taxonomy (INELIGIBLE, BUSY, PR_OPENED, FAILED, UNAVAILABLE, DISABLED, etc.) with per-case recovery makes the behavior predictable in a way no annotation could.

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?

Front-loaded correctly: what it does, then the order of operations, then the result semantics. Every clause carries recovery information, but it is delivered as one unbroken wall of text with a status-code dump that would be far more scannable as a short list.

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?

There is no output schema, so the description must explain returns — and it does, covering both the immediate answer and the deferred fix block on get_issue. Given an async mutation with a rich failure taxonomy and only two parameters, nothing an agent needs in order to call it, interpret it, or recover from an error is missing.

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 100%, so both parameters are already documented; the description only adds provenance for the fingerprint (it comes from the investigation block via get_issue/list_issues). The optional hint parameter is never mentioned in the description at all, so the schema does the remaining work. Baseline 3 is appropriate.

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 ("open a draft pull request that fixes one issue") plus scope (caller's account, customer's own repository). It is unambiguously distinguishable from siblings like get_issue, list_issues, and start_investigation, which it names explicitly.

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?

Gives an explicit prerequisite chain: list_issues to pick an eligible issue, get_issue to read the investigation block, and only then fix_issue with a code-verified root cause. It also routes to the alternative tool (start_investigation) for the NO_BRIEF case and tells the agent when NOT to call (ISSUE_NOT_OPEN, NOT_AN_ISSUE).

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