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

Goes well beyond the annotations: it discloses that the work is asynchronous ('made in the background'), serialized and rate-limited ('one at a time and once a day'), retained for a year, and requires human confirmation before starting. These are exactly the traits an agent needs and none of them are in the annotation set.

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 short sentences, zero filler, with scope first, then execution constraints, then the confirmation instruction. Each sentence contributes distinct, actionable information.

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?

With no output schema, the description should say what the call returns (a job/export identifier) and how to follow progress, since the operation is explicitly asynchronous. Retention and quota are covered, but the post-call path is left to inference.

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?

Zero parameters, so the baseline is 4 and there is nothing further the description could clarifying; the whole-workspace scope is nonetheless stated, which is the meaningful semantic here.

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 concrete verb and resource ('Start making a zip of the whole workspace') with the exact scope, and grounds it against a user-visible reference ('as Export now on the Export page does'). It does not name the sibling tools that read the resulting export (getExport, listExports), so differentiation is inferred rather than stated.

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?

'Ask the person first' is an explicit confirmation requirement, and 'one at a time and once a day' tells the agent the daily quota so it won't retry in a loop. There is no statement of what to do when the quota is exhausted (e.g., use getExport/listExports to check the existing export), so the alternative path is missing.

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