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

The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds one useful behavioral note — that state is volatile and should be re-polled rather than assumed — but says nothing about what the states look like or whether a build may appear between polls.

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: the first states what is returned, the second states the operational habit. Nothing is padded and the core purpose is front-loaded.

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 simple single-parameter read with no output schema, the description tells the agent both what comes back conceptually (running flag plus latest state) and how to use it. The only gap is enumerating possible build states, which is minor.

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?

There is a single parameter with 100% schema description coverage ("Project UUID"), which the schema fully documents. The description adds no further meaning about the identifier, so baseline 3 applies.

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 verb and resource: reads a project's current build-running flag plus latest build state. It is clear on its own, but it doesn't distinguish itself from nearby siblings such as list_builds or get_deployment_status, which an agent could easily mistake for the same question.

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?

"Poll this rather than assuming a build finished" gives a genuine usage cue about repeated invocation after triggering a build. However, no alternatives or exclusions are named, so the agent gets no guidance on when list_builds or get_deployment_status would be the better call.

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