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

Annotations only state the safety profile (destructive=true, idempotent=false, openWorld=true); the description adds the economics and lifecycle that annotations cannot express: successful calls are charged, provider failures are not, pending runs poll for up to 25 seconds, and truncated results must not be retried. Nothing here contradicts the destructive/non-idempotent hints — the no-retry rule reinforces 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?

Six short sentences, each carrying a rule (cost, failure billing, polling window, retry ban) and front-loaded with the core action. The opening 'using the REST billing and access controls' and the trailing 'Models use their documented REST endpoint' are boilerplate/unclear enough to cost a point, but there is no padding.

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 no-output-schema, open-world execution wrapper, the description covers cost model, failure charging, polling window, fallback tool, and retry prohibition — the operational facts an agent needs. What is missing is any notion of what the target tool's input should look like or what a returned run result contains (status, output, id), which the agent must guess.

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 0% for both required parameters, so the description must carry the burden and it does not: it never states the format of 'tool' (name? slug? namespaced id?) nor the shape of the free-form 'input' object passed to the target tool. The line 'Models use their documented REST endpoint' gestures at input semantics but is too vague to be actionable.

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?

Starts with a concrete verb+resource pair ('Execute a public tool') and immediately frames the billing/access model, which is the distinguishing trait versus siblings get_run, inspect_tool and search_tools. It explicitly routes the agent: 'Inspect first' (inspect_tool) and 'use get_run to check later' (get_run). An agent can pick this tool apart from its siblings without opening a 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 an explicit ordering rule ('Inspect first'), an explicit alternative for polling ('use get_run … without starting another execution'), and a hard when-not-to condition ('Truncated or unsupported results must not be retried'). This is close to a full when/when-not/alternative matrix.

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