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

Annotations declare a destructive, non-idempotent, open-world write, and the description adds credit cost (18–26), automatic refunds on failure, the ~2–3 minute minimum latency with polling guidance, and the render-vs-manifest output difference — all context beyond the structured fields.

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 core action and cost, then sequencing, then timing, then render behavior. Dense with heavy all-caps emphasis and em-dashes, but nearly every clause carries operational value; mildly over-signposted.

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?

Covers cost, prerequisites, async lifecycle, follow-up polling, timing expectations, render output differences, and failure refunds. With an output schema present for the job result, nothing essential is missing for correct invocation.

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 86%, so the schema already documents most params. The description still adds meaningful semantics for render (inline viewable assets vs. layered manifest opened via dashboard viewUrl) and reinforces the brandId dependency, going beyond the schema's terse '+3 credits' note.

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+mode: 'Kick off an ASYNC snack generation job for a brand'. This distinguishes it from siblings like generate_influencer_snack, create_slides, and generate_meme by naming the async job nature and brand scoping.

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 prerequisite steps ('call estimate_snack_cost first', 'call list_brands first, or create_brand'), the follow-up tool (poll get_job), and when to pass render=true. An agent has a complete routing path.

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