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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered; the description adds the genuinely useful behavioral fact that status is asynchronous and progresses to one of three terminal states. It does not say whether a ready downloadUrl expires or how errors are surfaced across polls.

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?

Two sentences, zero filler, and the payload contents are front-loaded before the polling instruction. Every clause 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?

With an output schema present and annotations covering safety, the description only needs the async/polling contract — which it supplies, including terminal states. Minor gaps (poll interval guidance, downloadUrl lifetime) keep it from being fully complete.

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% and both parameters are documented there (exportId format vg_expo_..., projectId provenance), so the schema carries the load. The description adds no parameter-level meaning beyond naming return fields, which is the baseline 3 case.

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 ('Return an export snapshot') and enumerates what comes back (status, progress, errors, downloadUrl, exportFileId, thumbnailUrl, file metadata), so an agent knows this is the retrieval half of the export flow. It does not name the sibling export_project as the initiator that produces the exportId, leaving that differentiation to the schema.

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?

'Poll until status is succeeded, failed, or cancelled' gives an explicit usage pattern plus the exact terminal conditions that justify repeated calls. It stops short of stating polling cadence, timeout behavior, or what to do after a terminal failure state.

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