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

Beyond annotations, the description reveals the async job model: tasks are durable, return an ID immediately, and require polling or cancellation. It also discloses client compatibility constraints. These are meaningful behavioral traits not captured by readOnlyHint, destructiveHint, or idempotentHint, and there is no contradiction with annotations.

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 three short sentences with the core action and result front-loaded. Every sentence serves a purpose: what the tool does, how to follow up, and compatibility guidance.

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 an async job-starting tool, the description covers the full workflow: start, poll, cancel, and client compatibility. The presence of an output schema and detailed nested argument schema means return shape and parameter details are already available, so nothing essential for correct invocation is missing.

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?

Top-level schema description coverage is only 33%; operation and arguments lack descriptions, and the tool description does not explain the operation enum or how to structure the arguments object. The nested argument properties are documented in the schema, but the description itself adds almost no parameter-level guidance to compensate for the low coverage.

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 action (start), the resource (a durable export or report job), and the immediate result (return its ID). It also distinguishes this from lifecycle tools like get_task and cancel_task by positioning start_task as the creation step. No vague phrasing or tautology.

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?

The description gives concrete lifecycle guidance: poll get_task at the returned interval, or use cancel_task, and notes compatibility with clients lacking the experimental MCP tasks extension. It does not explicitly contrast start_task with synchronous export/report siblings, but the intended usage context is clear.

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