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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine workflow context — that this is a polling follow-up to vectorize_image — which is valuable beyond the annotations. It stops short of describing polling behavior (frequency, cost, whether it consumes credits like get_credits suggests) or what changes between a running and a completed conversion.

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?

A single sentence with the trigger condition front-loaded, which is exactly the right ordering for a polling tool. Minor awkwardness in the informal 'how it stands and its figures' phrasing, but nothing is wasted.

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?

There is no output schema, so the description carries the burden of explaining return values, and 'its figures' is too vague to tell an agent what fields to expect (status, progress, dimensions, credit cost). For a simple one-parameter read tool this is only adequate — the trigger is covered, the payload is not.

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 coverage is 100% and the single parameter is already documented in the schema as 'The conversion_id vectorize_image answered.' The description adds no meaning beyond that — it restates the same link to vectorize_image without explaining where the ID originates or what an invalid ID does. Baseline 3 applies when the schema carries the parameter semantics.

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 verb ('read') and resource ('a conversion'), and states what is retrieved ('how it stands and its figures' — status plus metrics). It is clearly narrower than siblings like start_conversion or vectorize_image, though the phrase 'how it stands' is looser than a direct 'returns the conversion status'.

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?

Explicitly anchors usage to a triggering condition: call this when vectorize_image reported the conversion is still running. That is concrete when-to-use guidance an agent can act on. It omits any when-not guidance, such as what to do once the conversion has finished or which other tool to prefer for fetching finished output.

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