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

The annotations provide only openWorldHint=true, so the description carries the safety burden. It does an excellent job: it discloses that the platform will reject non-failed builds as a protective measure, and explains the semantics of retry (when meaningful vs futile). It also explains the `deploy` parameter default behavior. The warning about retry being pointless for code failures is valuable behavioral context beyond the schema.

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?

The description is well-structured with clear paragraphs: purpose statement, explicit state constraints with a warning, and a usage decision guide. It's somewhat longer than the TDQS high example but every sentence earns its place — the state constraint, protection note, and retry semantics are all essential. No filler or redundancy.

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 state-sensitive mutation tool with only openWorldHint annotation and an output schema present, the description is remarkably complete. It covers: valid input conditions (failed state), platform rejection behavior, the decision framework (external vs code failure), the recommended workflow order (diagnose → fix → retry), and the sibling tool used in that workflow. This is comprehensive for a two-parameter tool.

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 coverage is 100% — both `project` and `deploy` have descriptions. The description adds marginal value: it restates that `deploy` defaults to the latest build when omitted (which the schema's default=null partially conveys). The description doesn't add syntax details beyond the schema, so baseline 3 is appropriate.

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 description clearly states the verb+resource+condition: 'Поставить упавшую сборку в очередь заново' (requeue a failed build). It specifies the state constraint (only `failed` builds). This distinguishes it from siblings like `cancel_deploy`, `deploy_logs`, and `rollback` which have different purposes.

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?

The description is exceptionally explicit about when to use this tool: ONLY for builds in `failed` state, and it explicitly warns that queued/building builds will be rejected by the platform (a protection, not an error). It also provides decision guidance: retry only makes sense for external causes (network, registry, timeout); for code failures it gives a full workflow: diagnose_deploy → fix → then retry. This explicitly names the alternative `diagnose_deploy`.

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