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

Annotations only declare this a safe, idempotent, non-open read, and the description adds a large amount beyond that: the full phase lifecycle, the meaning of superseded/checking/refused/starting/crashed, the trap that a working URL does not prove the new release is live, and that state_reason and failure_excerpt explain failures. That is exactly the operational context annotations cannot carry.

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?

Content is front-loaded with return values and then polling and state semantics, which is the right order, and with no output schema the detail earns its place. However the opening sentence is an extremely long run-on with a giant embedded parenthetical of phase names, making it hard to parse at a glance; tighter sentence breaks would preserve the same information more legibly.

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?

There is no output schema and no structured state documentation, so the description must carry the return semantics entirely, and it does: states, phases, log behavior, deploy_state values, and the fields that explain failures. An agent has everything needed to poll correctly, interpret terminal states, and decide what to do next.

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% and both parameters are already documented, including the default-org behavior for org_name. The description only implies build_id comes from publish_app, which the schema already states, so there is no added parameter meaning beyond structured data.

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 specific resource (the build that publish_app started) and enumerates exactly what is returned: state, phase, logs, and, on success, release, URL, and deploy state. It explicitly ties itself to the publish_app sibling and to get_evaluation for the checking path, so an agent can distinguish it from get_logs, get_service, or get_evaluation without opening any schema.

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?

Gives concrete when/when-not guidance: poll every 10-15 seconds until deploy_state is up, crashed, or refused, or the build failed or was superseded, with the expectation that most deploys finish within five minutes. It routes to named alternatives for specific sub-cases (get_evaluation with wait_seconds 20 for checking, follow the newer build after superseded) rather than leaving the agent to guess.

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