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

Adds substantive behavior beyond the annotations: no generation occurs, no credits are consumed, no sign-in is required, and the call returns settings plus the credits that would be required. Annotations only supply the generic safety profile (readOnlyHint=false, destructiveHint=false), so this cost/no-op disclosure is genuinely additive. Mild tension with readOnlyHint=false exists, but since 'prepare' can create a preparation artifact, this is not a contradiction.

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?

Front-loaded with purpose and deliverable, then constraints, which is the right order. It loses a point for redundancy: 'no presenter on camera' appears twice and the 'original visuals only' constraint partially restates the earlier exclusions.

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 single-required-parameter preparation tool with an output schema present, the description covers everything an agent needs: what is produced, what is not produced, cost implications, auth requirements, and content restrictions. Return values are already handled by the output schema, so nothing material 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?

Schema description coverage is 100%, with topic, style, and audience all documented in-schema, so the baseline is 3. The description's video traits (30 seconds, four scenes, voiceover) inform output expectations rather than adding meaning to any parameter, so it does not exceed baseline.

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 ('Prepare an animated explainer video'), and pins down the concrete deliverable: ~30 seconds, four illustrated scenes with motion and voiceover, no presenter, one MP4. This is specific enough that an agent can distinguish it from the sibling generate_result/get_result tools without opening a 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?

Explicit when-to-use ('new animated videos from text only, with no presenter on camera') and explicit when-not ('do not use it for uploaded footage, photos, real people, editing or captions'). It also clarifies the boundary with generation ('Nothing is generated and no credits are spent'), which is exactly the disambiguation an agent needs against generate_result.

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