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

Annotations only say this is a non-read-only, non-idempotent, non-destructive write. The description adds the critical economics: the call spends the user's credits, max_credits acts as an agreed price cap, and a no-answer call may already have started, so list_photos should be checked before retrying. That is exactly the behavioral context annotations cannot carry.

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 short sentences, each carrying distinct information: what it does, how to price it, and how to recover from a timeout. Slightly dense but front-loaded and free of 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 two-parameter paid mutation with no output schema and no annotations beyond hints, the description covers cost, price source, and duplicate-call risk, which are the failure modes that matter. It could still say what a successful call returns, but the essential calling information is present.

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 compensate, and it does for max_credits: it is the price the user agreed to, sourced from get_shoot or list_photos, which explains both meaning and value provenance. photo_id is left to be inferred as the photo to regenerate.

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?

"Makes the same photo again, a new take of the same look" gives a concrete verb and resource and implicitly separates it from edit/upscale/zoom_in, which transform rather than regenerate. It stops short of naming the alternatives explicitly, so the distinction is inferable rather than stated.

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?

It tells the agent where to source max_credits (get_shoot or list_photos) and gives a concrete retry procedure after an unanswered call. It does not say when to choose reroll over sibling generators like add_photo or start_shoot, so sibling routing guidance is incomplete.

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