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

Annotations provide only openWorldHint=true (no read/destructive hints). The description adds valuable behavioral context by clarifying that the live site address is unaffected and retains the previous version — a key safety reassurance. However, it doesn't disclose what happens to partial artifacts, whether cancel is reversible, or any timeout/permission requirements. For a mutating operation with only openWorldHint, this is adequate but not rich.

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 exceptionally compact — two short sentences. The first states the core action, and the second provides the most important safety distinction. Zero filler, front-loaded purpose.

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 2-param tool with an output schema and 100% schema coverage, the description covers the key behavioral nuance (live address unchanged). The openWorldHint provides context. It's slightly short on details around cancellation semantics (e.g., what happens if build already finished), but is near-complete for the tool's simplicity.

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 the description mentions the default behavior ('Без него берётся самая свежая' — without it the most recent is taken) for the deploy param, which adds value beyond the schema. However, the project param instructions are exclusively in the schema, and the description doesn't add cross-tool guidance about slug extraction, so it roughly meets the baseline.

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 'Остановить сборку, которая ещё идёт' (stop a build that is still running) with a specific verb+resource combination. It further differentiates by explaining the live address remains unchanged, which distinguishes it from publish/rollback/sibling operations.

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 implies usage for in-progress builds and clarifies the non-destructive effect on the live address. However, it doesn't explicitly contrast with retry_deploy or diagnose_deploy siblings or state conditions for when cancellation isn't possible (e.g., already completed builds), though the 'ещё идёт' phrasing implicitly excludes those.

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