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

With no annotations, the description carries the full burden. It discloses the polling semantics (progress or completed result), which is genuinely useful. However, it omits error behaviors — what happens with an invalid/expired ticket, whether it can be called repeatedly, or any rate-limit considerations.

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?

A single well-structured sentence front-loads the core purpose and appends the key constraint. Zero wasted words — every element earns its place.

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 simple one-parameter poll tool with no output schema and no nested objects, the description is largely sufficient — it states what is returned and the required input. The only gap is identifying that the ticket comes from compute_submit, which would round out the workflow.

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. 'ticket required' adds the meaning that the parameter is a token tied to a queued search, but it doesn't explain how the ticket is obtained or its format. It adds some value over the bare schema but leaves the most useful derivation detail unsaid.

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 states a precise operation — 'returns a queued search: how far it has got, or its result once finished.' The verb+resource are specific, and the distinction between progress and final result clearly separates this from compute_submit (which can be inferred as the submission counterpart).

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?

'ticket required' implicitly tells the agent a prior action produced the ticket, but the description never names the source sibling (compute_submit) or states when to poll versus wait. The context is clear enough to guess, but no explicit when-to-use or alternative routing is provided.

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