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

Annotations already declare this is a non-read-only, open-world, non-idempotent, non-destructive action, and the description stays consistent with that by framing it as "starts work." It adds real behavior beyond annotations: the call yields the fork and branch to commit on, and a supplied reason is placed first in the brief as the contributor's instruction. The description does not mention permissions, state changes on the PR, or whether the action can be undone, which caps it at 4.

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?

Two sentences, front-loaded with the action and its output, followed by the usage condition and the exclusion. It is dense with parentheticals ("reviews, comments, checks") and one compound clause, but no sentence is 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?

For a two-param mutation tool with no output schema, the description covers the essential gaps: what the call returns (fork and branch), where the optional reason lands, and when the tool is inappropriate. It stops short of describing side effects on the PR or failure modes, which is the remaining gap.

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%, including patterns and maxLength, so the baseline would be 3. The description earns a point above baseline by explaining an effect the schema does not: the `reason` text is positioned first in the brief as the contributor's instruction. `prId` is not discussed in prose, but the schema already defines it as the GitHub node id from the contributions list.

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?

"Starts work on one of your open pull requests (reviews, comments, checks), and answers its brief with the fork and branch to commit on" gives a specific verb, a bounded resource, and even the shape of the result. The scope is further narrowed by the exclusion "Not for a pull request you opened by hand," so an agent can distinguish this from other start_* tools. It does not name a sibling alternative, which keeps it just short of a 5.

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 when-to-use condition is stated concretely: "For a pull request marked followUpRecommended, or when the contributor thinks something is wrong." The when-not is also explicit: "Not for a pull request you opened by hand." What is missing is the alternative to use instead for a hand-opened PR, so the routing is incomplete rather than fully explicit.

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