get_task

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

With no annotations, the description carries full behavioral burden and does disclose real traits: long-polling semantics via wait_seconds, that full prompts/research packets are retained in artifacts, and that truncated answers are explicitly labeled. It still omits error behavior, auth needs, and what happens when a task is absent or still running.

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 dense sentences with the return content front-loaded and no filler; each sentence carries information. The phrasing is slightly telegraphic ('when exposed'), but nothing is wasted.

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 4-param, no-output-schema, no-annotation tool, the description does a fair job covering return shape (compact vs full, token counters, truncation labeling) and the polling model. The remaining gap is the identifier parameters and the one-of task_id/workflow_id requirement, which the description never addresses.

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 0%, so the description must compensate. It adds genuine meaning for two params (wait_seconds as an anti-polling delay, detail=full as an opt-in to artifacts), but says nothing about task_id vs workflow_id or the anyOf constraint requiring one of them, leaving the most important identifier semantics undocumented.

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 conveys what the tool returns (compact results, token counters, artifact-retained prompts) and the name get_task signals retrieval, so an agent can roughly infer the purpose. However, it never states the core operation plainly (fetch a task's results/status by id) and offers no differentiation from siblings like cancel_task or list_workers.

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?

It gives two concrete usage cues: use wait_seconds up to 45 instead of repeated polling, and request detail=full only when artifacts are actually needed. What is missing is any guidance on when to call this versus siblings (e.g., after submit_task, instead of cancel_task), so usage is only implied.

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