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

Annotations declare destructiveHint=true, and the description adds real behavior beyond that: 'WRITE — starts compute', the cascading retry of dependent skipped jobs, and the failure precondition when a dependent job already started. It doesn't cover auth or return semantics, but for a mutation tool this discloses the important side effects and pitfalls.

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?

Front-loads the WRITE warning, then states action, cascade behavior, and the fallback alternative in three tight sentences with 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?

For a mutation tool with no output schema and full parameter coverage, the description supplies the essentials: mutation nature, cascade scope, and the failure/alternative path. Return-value behavior is the only omission, which is minor given no output schema.

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%, so both parameters (job_id, workflow_id) are already documented, including the workflow_id provenance hint. The description adds no additional parameter semantics beyond what the schema provides, 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 precise verb+resource: retry one failed or cancelled Depot CI job. It also specifies the cascade scope ('plus any skipped jobs that depend on it'), which distinguishes it from sibling retry/cancel tools.

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?

Explicitly names the alternative depot_ci_retry_failed_jobs and the exact condition that selects it ('Fails if a dependent job already started; use ... then'). This is explicit when-to-use and when-to-switch guidance.

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