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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the polling contract: each call re-issues a fresh capability rather than returning a cached one. It does not say what a poll returns when conversion is still running (error vs. pending status), which is the single most important behavior for a polling tool.

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, and the polling purpose and the filter constraint are both front-loaded. Nothing could be cut without losing 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?

Covers the identity/scope question well, but for a nested-object, zero-coverage schema with no output schema and no annotations covering return shape, the description leaves the not-ready case and the format/expiresIn parameters undefined. An agent can call it, but cannot reliably interpret the response.

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 0%, so the description must compensate: it clarifies that the filter must match the prepare call exactly, which is genuinely useful semantics. But it says nothing about the sibling parameters inside the required nested `download` object (format, expiresIn), nor whether format must match the original request.

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 ('a prepared geospatial export') and describes the outcome ('return a fresh download capability once the format conversion is ready'), which clearly separates it from source_prepare_download. It never names the sibling that creates the export, so the pairing is only implied.

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 an explicit precondition ('Repeat the same filter used to prepare the export') and an explicit exclusion ('a different filter is a different artifact and it is not enqueued here'). It stops short of naming the tool to call first when nothing has been prepared.

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