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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses the polling loop semantics, that a pending status accompanied by a review_url means the user has not decided yet, and that final_text must be used verbatim. That is substantive behavioral context an agent could not infer from annotations or schema.

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 polling trigger is front-loaded and the sentences are dense with actionable content, but the trailing guidance about keep_original and removed_padding belongs to the sibling tools and slightly dilutes focus. Nothing is redundant, though, and each clause maps to a real agent decision.

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 polling tool with an output schema, the description covers the entry condition, the re-call loop, the terminal handling of final_text, and the sibling escape hatch. Return values need not be restated because an output schema exists and the description points to rewrite's shape.

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%, so both 'id' and 'max_wait_seconds' (including the 240 default and 540 cap) are already fully documented. The description adds only the provenance of 'id' ('that id' from rewrite), and says nothing about wait behavior or the zero-check option, so it does not meaningfully exceed the schema.

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 names a specific action ('waits for the result of that id') and states the return contract ('returns the same fields as rewrite'), which lets an agent distinguish it from rewrite and keep_original without opening the schema. The trigger condition ('when rewrite or keep_original returned status pending') further pins down what this tool uniquely does.

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 an explicit entry condition (a pending status from rewrite or keep_original), an explicit loop instruction ('make sure the user has the link, then call it again'), and an explicit alternative with its own condition ('Call keep_original only for a changed fact, name, number, date, yes or no or promise'). It also pre-empts a wrong action by noting that removed_padding is not a reason to call keep_original.

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