Ask to change where CI runs (needs approval)

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

Goes far beyond the annotations: it discloses the fresh-preview diff Mushi builds, the optimistic-concurrency check that the variable must still match at run time, double policy evaluation, the one-hour approval window in the console, and the specific error codes returned. It also explicitly bounds the blast radius ('Mushi never changes runner labels or registrations'), which neither destructiveHint=false nor openWorldHint=true conveys.

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 with the action and its scope, then constraints, then return/error contract; sentences are dense but each carries distinct information. Slightly long and the trailing 'Write.' marker adds no value.

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 mutation tool with no output schema and five parameters, the description supplies the approval workflow, the success payload shape ({ id, status, payloadSha256, preview }), the error taxonomy, and the human-confirmation requirement. Nothing an agent needs in order to call it correctly 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 baseline is 3, but the description adds real semantics the schema cannot express: the allow-list rationale for variable names, what null means operationally, and the run-time equality constraint on the current value. repo, reason, and projectId get no additional narrative beyond the schema.

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 opening sentence names a specific verb (ask to change), the exact resource (one repo Actions variable read in runs-on), and the mechanism (set or remove LINUX_RUNNER / RUNNER_<WORKFLOW>). It is clearly distinguishable from siblings like get_ci_overview or refresh_ci, which read or trigger CI rather than request a placement change.

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 conditions are unusually explicit: only two variable names are mutable, null means remove-and-fall-back, and 'Confirm with the user first' plus the approval-only nature tells the agent exactly how to proceed. It does not, however, point at a sibling for inspecting current runner configuration or costs before filing the request.

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