diffci_run_affected_tests

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

Annotations declare readOnlyHint=false and openWorldHint=false, so the agent already knows this is a non-read-only, closed-world operation, and the description is consistent with that. Beyond the annotations, the description usefully discloses the result-authority caveat versus CI and the possibility of an expensive conservative full-suite fallback. It does not say what state is written, how long a full run may take, or how the timeout interacts with that fallback.

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 the fallback behavior, with no filler. The main clause is slightly dense and could be split, but nothing is wasted.

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 what a run produces, yet it never says whether the result is a pass/fail, a selected-test list, or a report path. For a tool that may execute a full test suite, the omission of return shape and cost/blocking characteristics leaves an agent unable to predict the outcome of invoking it.

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?

Two parameters with only 50% schema description coverage: repo is documented in the schema, but timeoutMs has no description anywhere. The tool description adds nothing about either parameter, not even that timeoutMs bounds the potentially long fallback run, so it does not compensate for the coverage gap.

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 names a specific action and target: reanalyze and verify the current working-tree snapshot using affected tests, with a full-suite fallback. That is concrete enough for an agent to know what the tool does, but it draws no line between itself and near-identical siblings such as diffci_verify_changed, diffci_verify, or diffci_check.

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 only usage signal is the trailing clause that required CI remains authoritative, which hints this is a local pre-flight rather than a replacement for CI. There is no explicit when-to-use, no when-not-to-use, and no mention of any of the nine sibling tools despite obvious overlap with the other diffci_verify_* tools.

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