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

Annotations already declare readOnly/idempotent/non-destructive/no-open-world, so safety is covered. The description adds genuinely non-structured behavior: that completed exports yield a short-lived download URL, which tells the agent to re-poll and to consume the URL promptly.

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, no filler, with the core action front-loaded and the output caveat second. Every clause carries 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?

For a one-parameter status-poll tool with no output schema, the description covers the essential return behavior (download URL on completion). It stops short of describing non-terminal states or whether import jobs ever produce a URL, but nothing blocking is missing.

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?

Single parameter with 100% schema description coverage; the schema already explains job_id and its provenance ('returned by export_vault or fetch_url'). The description adds no additional parameter meaning, so the baseline 3 applies.

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 ('Poll') and resource ('vault import or export job'), which cleanly separates it from the sibling vault_status (vault-level) and run_status (run-level). The second sentence adds the distinguishing scope detail that finished exports carry a download URL.

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?

Usage is implied by 'poll' — it is the tool you call repeatedly to track an async job — but no alternative is named and no when-not condition is given (e.g. use vault_status for overall vault state). Adequate but leaves routing to inference.

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