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

Annotations only declare readOnly=false/idempotent=false; the description adds the high-value context the annotations lack: save defaults to false so the founder reviews first, the call consumes one AI generation turn, it costs no Ad Run credit, and it deliberately does not write the conversion-critical sign-up fields. These are concrete side-effect and cost disclosures.

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 purpose sentence, then prerequisites, args, returns, boundary note, and cost note in labeled blocks. Every sentence carries actionable information with no padding.

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?

No formal output schema exists, but the description documents the return shape, the prerequisites, the mutation semantics, and the cost implications. For a generative, credit-consuming mutation tool, this covers everything an agent needs to invoke it correctly.

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 0%, so the description must carry the load. It fully explains save (write behavior and default), but ideaId is only implied and response_format (a schema enum) is undocumented in prose. It compensates well for one parameter but not all three.

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+resource ('Generate the ad creative for an idea') and enumerates the exact artifacts produced (tagline, primary/secondary ad text, image prompt, sign-up page copy). The agent can distinguish it from siblings like generate_hero_image or draft_brief without opening any 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?

Explicitly names the prerequisite path ('call idealaunch_draft_brief and idealaunch_update_idea_brief first if it is not [a complete brief]') and defines the boundary against idealaunch_update_idea_brief for sign-up headline/description/CTA. Both when-to-use and when-not-to-use are stated.

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