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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description complements by detailing what the tool returns (HTTP status of public URL vs private interface, container table, host metrics, .env key names), and notably explains that timed_out:true is not a failure — the build is still running. It also mentions that status alone decides success, and advises to fetch build_log from get_deployment on build_failed. This adds significant behavioral context beyond annotations without contradicting them.

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 concise and front-loaded with the key instruction ('CALL THIS INSTEAD OF POLLING'), then layers relevant details: what it returns, how to handle timeouts, and when to fall back to get_deployment. Every sentence adds essential information with zero fluff. The emoji and caps are purposeful to draw attention but don't distract.

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?

Given the output schema exists and annotations are strong (read-only, idempotent), the description covers all critical aspects: when to use, what it returns, timeout semantics, and fallback strategy on failure. It also addresses the potential pitfall of the private interface returning 401 while the public path 502s. For a tool with modest complexity, this is complete.

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 id and timeout_s are well described in the schema. The description adds the timeout semantics: it explains that timed_out:true means the build is still running and suggests calling again, and that a typical deploy takes 90-250 seconds. This adds value beyond the raw schema, though the schema already does most of the work, so a 4 is justified rather than 5.

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 blocks until a deployment reaches a terminal state and returns comprehensive evidence in one response. It distinguishes from sibling get_deployment by explicitly saying 'CALL THIS INSTEAD OF POLLING' and contrasting with get_deployment. The purpose is specific and actionable.

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 instructs when to use (instead of polling get_deployment) and when not to (do NOT loop on get_deployment; on build_failed/error call get_deployment for build log). Provides clear context on timeout behavior and indicates when to call again with a larger timeout. This is textbook usage guidance.

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