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

Annotations already cover read-only safety, and the description still adds real behavioral context beyond them: the 'repo' scope / OAuth write:repo requirement, that every token read is audited, and that a truncated step exposes `fullLog` as an artifact download. It stops short of stating pagination, size limits, or latency, which is the only remaining gap.

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?

Purpose is front-loaded, but the middle is a single dense run of nested parentheticals describing testFailures categories and forensic fields that is difficult to parse on one read. The detail is largely justified because there is no output schema, but the packing is heavy for the payload.

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 carries the return shape itself: run metadata, per-job/per-step status, exit code, duration, failedSteps, testFailures with its classification taxonomy, and fullLog. Combined with the auth note this is close to complete, with only pagination/size expectations absent.

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?

With 60% schema coverage, the description compensates by explaining `step` (a name exact-then-substring case-insensitive, or 1-based position within its job) and the interaction rule that full logs appear only when neither `step` nor `tail_lines` is passed. It adds meaning beyond the schema, though `owner`/`repo` are left entirely to 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 and resource ('Return a workflow run's logs plus a failure summary') and adds a scope distinction via 'JSON-friendly companion to the ZIP-download endpoint'. It never names an actual sibling tool (e.g. get_workflow_run, explain_failure), so the differentiation is by shape of output rather than by sibling routing.

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 implied through parameter behavior rather than stated as guidance: '`step` ... returns only that step's stdout/stderr; `tail_lines` keeps the last N lines. The full per-job logs are included only when neither is given.' There is no explicit statement of when to prefer this over explain_failure or get_workflow_run, nor any exclusion.

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