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

The description adds meaningful behavioral context beyond the annotations: it explains that polling is 'server-side', that it continues until a terminal state or timeout, and that it is read-only. The read-only claim aligns with the readOnlyHint annotation, and no contradictions exist. While it could detail what happens on timeout or cancellation (e.g., returned response), the output schema likely covers that, so this is sufficient.

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 a single, well-structured sentence that front-loads the core purpose and then adds the key differentiator ('read-only and cheaper'). Every clause earns its place, with no wasted words. It is concise yet informative.

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?

Given the tool's moderate complexity, the presence of an output schema, and thorough annotations, the description is complete enough. It covers the core behavior (server-side polling until result, terminal state, or timeout), the read-only nature, and the cost benefit. It does not need to explain return values since an output schema is present. The description provides all necessary context for correct selection and invocation.

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 100%, and each parameter has a detailed description in the schema (task_id with source, timeout_seconds and poll_interval_seconds with ranges and defaults). The tool description itself does not add parameter semantics beyond what the schema provides. Per the rubric, baseline is 3 when schema coverage is high, and the description adds no additional value for parameters.

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 uses a specific verb ('Poll') and clearly states the resource ('a crawl task server-side') and the termination conditions ('has a result, reaches a terminal failure/cancelled state, or the bounded timeout expires'). This distinguishes it from sibling tools like get_task_status, which likely performs a single status check rather than a server-side blocking wait.

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 explicitly states when to use the tool: when you need to wait for task completion and want to avoid repeated manual polling, noting it is 'cheaper for agent context'. It does not explicitly name alternatives or exclusions, but the contrast with 'repeated manual polling' implies the alternative of using get_task_status in a loop. This provides clear usage context without being overly verbose.

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