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

Adds real behavioral context beyond the annotations: no credits charged, no sign-in required, and the exact shape of what comes back (scene count, credits, link). The one unreconciled point is that annotations declare readOnlyHint=false and idempotentHint=false while the description reads as side-effect-free; the description never explains the residual server-side state (e.g. a stored brief) that justifies those hints, so a small transparency gap remains.

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 the action and the return payload, then usage and exclusions. Three sentences, each doing distinct work, with no filler or repetition of the title.

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 9-parameter planning tool with an output schema, the description covers the action, the non-billing/non-auth behavior, the return contents, and the full exclusion boundary. Nothing an agent needs before calling is missing, and return-value detail is correctly delegated to the output schema.

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%, so every parameter is already documented in-schema. The description only restates the optional parameter list in a parenthetical and adds no defaults, formats, or interaction rules beyond what the schema provides, so the baseline of 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 and resource ('Prepare a UGC video ad brief ... from the product description and target audience') and immediately clarifies the output ('Returns the plan: scene count, credits required and the ManyMotions link'). The 'Nothing is generated' clause functionally distinguishes it from the sibling generate_ugc_video_ad without the agent needing to open either 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?

Provides an explicit inclusion condition ('only for a new short AI video ad about a product, brand, app or service ... with an AI presenter and voice') and pairs it with a concrete exclusion list: editing uploaded video, captions on existing footage, real human creators, still images, logos, non-advertising videos. This is a textbook when/when-not pair.

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