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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description adds what the annotations cannot — quota cost and refund behavior, and the asynchronous id-then-poll contract. These are the two facts an agent most needs to avoid wasting a drawing or misreading an immediate empty response.

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 dense paragraph, but front-loaded with the purpose and with no filler sentences — quota, refund, and polling all earn their place. The archaic, clause-heavy phrasing costs a little readability compared with a plainly structured version, keeping it short of a 5.

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 correctly supplies the return contract (an id) and the completion protocol through get_described. Combined with quota/refund semantics and a fully documented schema, an agent has everything needed to call and follow up on this tool.

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% (both params documented, including the 24-char name and 300-char description limits), which sets a baseline of 3. The description goes beyond that by implying the description parameter is subject to content review ('a description refused'), telling the agent its input can be rejected, and by noting the invented-adult constraint on what may be described.

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 and resource ('Draw a presenter ... from a description of how they look') and constrains the output ('an adult, invented, not a real person or a character'). That constraint alone separates it from sibling tools and from a generic image-generation call, so an agent knows exactly what artifact this produces.

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 the operational context clearly: it is free but counted against a daily quota of 5, a refused description or failed drawing refunds the quota, and the call returns an id that must be polled via get_described 'every few seconds until its status is ready or refused'. It names the follow-up sibling and the polling cadence, though it never states an explicit when-not-to-use case (e.g. reuse an existing presenter via list_presenters/keep_presenter instead).

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