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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: the viewer is what the user actually sees, so the agent must follow up with one short line and must never paste URLs or markdown images. That post-invocation contract is not inferable from any structured field.

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?

Three sentences, front-loaded with what the tool does, then when to call it, then the required post-call behavior. Every sentence carries a distinct, actionable instruction with no filler.

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 one-parameter display tool with an output schema, an agent needs purpose, trigger, id source, and follow-up behavior — all four are present. Nothing material is left to inference.

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 already documents the 1-24 range, ordering, and valid id sources (list_creatives, search_library, get_job, get_upload). The description's mention of 'a finished job's results (its creative ids)' largely restates the schema, so it adds little beyond the 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 ('Show creatives to the user in the chat') and immediately clarifies the mechanism — Rawa's viewer renders each at its own shape with download, open and full-screen buttons. This clearly separates it from retrieval siblings like list_creatives, search_library and get_creative, which return data rather than display it.

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?

'Call this whenever the user wants to see creatives' gives an explicit trigger, and it enumerates the upstream sources whose output feeds it (finished job creative ids, list_creatives, search_library). It doesn't state a when-not or contrast case explicitly, but the trigger and source routing are strong enough that an agent can select it confidently.

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