rerun_failed

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

With no annotations, the description carries the burden and does reasonably well: it discloses the at-most-100 rerun cap, that the returned structure matches run_tests plus a rerun count, and that the stored failure list is replaced by remaining failures (a state mutation). It omits error behavior when no prior failure list exists and any permission/execution side effects.

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?

Three tight sentences, front-loaded with the core action, then return shape, then the 100-cap and failure-list replacement. No redundant or filler wording.

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?

The output schema and the description cover return values well, and the prerequisite of a prior run in the same session is stated. However, for a three-parameter tool with zero schema documentation, the absence of any parameter guidance leaves the definition only partially complete.

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 description coverage is 0% across three parameters (path, python, timeout), and the description does not mention any of them. The phrase 'this project' hints at path scoping, but there is no guidance on what python or timeout control, so the description fails to 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?

States a precise verb and resource ('Re-run only the tests that failed or errored') and constrains it to the last run_tests/rerun_failed in the same server session, which cleanly separates it from the sibling run_tests (full run) and list_tests.

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?

It implies the when: after a prior run_tests/rerun_failed has produced failures, within the same server session. That is a clear trigger context, but it never explicitly says when to prefer run_tests instead of this tool or what happens if there is no recorded failure list.

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