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

The annotations provide openWorldHint=true but no read-only/destructive hints, so the description carries the burden. It discloses a key behavioral fact: the live address is unchanged, leaving the previous version. However, it does not state whether cancellation is destructive to the deploy record, whether it can be resumed, or whether there are side effects beyond stopping the build.

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 short sentences, both earning their place. The first states the primary action clearly, and the second adds a crucial non-destructive guarantee. No fluff 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 cancellation tool with an output schema, a full return-format explanation is unnecessary. The description omits failure cases (what happens if no build is running, or if the build already finished) and does not clarify whether the cancel applies to the most recent deploy vs. the live one — though the deploy parameter default partially addresses this.

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?

The schema has 100% description coverage — project and deploy are both documented in the schema itself. The deploy parameter (optional, defaults to newest build) is meaningfully explained in the schema as "id сборки. Без него берётся самая свежая." The description adds little beyond what the schema already provides, 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 tool stops an in-progress build ("Остановить сборку, которая ещё идёт"). It identifies the verb (cancel/stop), the resource (build/deploy), and the scope (only in-progress ones). It distinguishes from siblings like deploy_logs, retry_deploy, and rollback by focusing on cancellation of an ongoing build.

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 establishes the key usage context: it only applies to builds "которые ещё идёт" (still running). It clarifies that the live URL is not affected — the previous version remains. This is a clear behavioral boundary, though it does not explicitly name sibling alternatives like rollback or retry_deploy for comparison.

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