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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is carried structurally. The description earns credit for going beyond that with a concrete consequence: 'A failed deploy job that now succeeds changes what is live' — an agent now understands the real-world blast radius, not just a boolean flag. It stops short of mentioning permissions or whether a new run attempt is created.

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 tight sentences: the operation and its scoping are front-loaded, and the second sentence justifies why the destructive behavior matters. Zero filler.

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?

With only two required, fully documented parameters, no output schema and full annotation coverage, the definition covers what an agent needs to invoke it, plus the live-state consequence. The remaining gap is return behavior — whether a new attempt/run id comes back — which matters for chaining into gh_actions but is unstated.

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 100% and both parameters (repo, run_id) are already documented in the schema, including the 'from gh_actions' provenance for run_id. The description restates that provenance but adds no format, constraint or edge-case detail beyond the schema, so baseline 3 applies.

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 specific verb and resource ('Run only the failed jobs of a GitHub Actions run again') with a scope qualifier ('only the failed jobs') that implicitly separates it from gh_actions_rerun, which re-runs the whole run. It never names that sibling outright, so the contrast is inferred rather than explicit.

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?

'by run_id from gh_actions' gives a useful prerequisite breadcrumb (fetch the run first via gh_actions), which is real workflow guidance. However, there is no statement of when to prefer this over gh_actions_rerun, nor any exclusion for in-progress or already-successful runs.

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