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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds rich behavior beyond that: a 45-second bounded wait, re-calling extends the wait, the three status outcomes with their payloads, the `can_retry` flag on error, and the session-scoped, one-day task_id lifetime.

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?

Four dense sentences, front-loaded with the action and the wait semantics, then the return contract, then the eligibility and lifetime caveats. No filler.

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?

No output schema exists, and the description compensates well by enumerating status values and their payloads. A minor gap remains around whether/how `result` refs should be passed back to `lca_get`, but overall an agent has what it needs.

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 100% and the schema already documents the id format, so baseline would be 3; the description adds genuine semantic value by explaining where the id originates (a previous tool call that returned a task_id) and its session/TTL constraints.

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 specific verb+resource: polls a long-running call identified by a `task_id` that was returned instead of a result. Clearly separable from siblings like `lca_get`, which it explicitly routes to for reading the saved object.

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 both the when ('only calls that returned a `task_id` have one') and the when-not ('a tool that returned its result directly has nothing to poll'), plus names `lca_get` as the alternative for retrieving the finished object.

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