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

The description says passing cancel stops the task and refunds credits — a state-changing, side-effecting operation — while annotations declare readOnlyHint=true and destructiveHint=false. That directly contradicts the declared safety profile an agent relies on to decide whether calling is harmless.

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?

Three compact sentences, front-loaded with the core purpose before the control options and the account prerequisite. Dense but nothing is wasted; only the trailing account note could be trimmed or moved to a prerequisite line.

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?

With no output schema, the description correctly carries the return-value burden: it names the state, the agents tried, and the final output. It also notes the free-account prerequisite. Remaining gaps are polling cadence and what states/exit conditions the agent should expect, but nothing essential to invoking it correctly is absent.

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 75%, but the description still adds meaning the schema does not: cancel refunds credits (the schema has no description for cancel at all), reply is specifically 'to answer an agent that asked for input', and task_id/route_id are traced to the tools that produce them. What's missing is guidance on which of task_id/route_id to supply, given neither is required.

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 concrete verb and resource ('Check a long-running task') and immediately identifies the two parameter sources (a task_id from call_api, a route_id from run_agent_task), tying it to the siblings that create the tasks. An agent can distinguish this polling/control tool from call_api and run_agent_task without opening the 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 clear context for when each mode applies: poll for state/output, pass cancel to stop and reclaim credits, pass reply to answer an agent that asked for input. It doesn't state when not to use it (e.g. vs list_my_api or re-invoking run_agent_task), so it falls just short of explicit alternatives.

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