coverage

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

readOnlyHint=true is consistent with 'read from', so no contradiction. The description usefully discloses the data source (pytest-cov report in logs), which implies results are unavailable if logs are absent or the project doesn't use pytest-cov, but it never says so outright or describes the failure mode.

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?

A single front-loaded sentence with zero filler; the resource and its source are both stated immediately.

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 covers the return shape, so that need not be explained. However, with 0% parameter coverage and no note on scope (the description says 'per job' while the input only accepts a run_id, implying a per-job breakdown of an aggregate call), an agent must guess at the mapping.

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% for two required parameters, so the schema gives no semantics for repo or run_id. The description does not mention either parameter, leaving the agent to infer that run_id is a CI run and repo scopes it.

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?

Specific verb and resource: reads total line coverage, and names the data source (pytest-cov report in job logs). It differentiates itself from generic siblings like job_log by being a derived metric, though it never explicitly contrasts with them.

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 is only implied: it should be used when you want coverage numbers, and the 'read from job logs' phrasing hints that logs must exist first. No explicit when-not or alternative (e.g. use job_log for raw output) is given.

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