Compose / edit several images

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

Annotations already declare non-readOnly, non-destructive, open-world, non-idempotent, so the mutation profile is known. The description adds genuinely new behavior — 'Runs as a queued job' — which explains why wait_seconds exists and implies a job_id return path, but it stays silent on cost, timeout behavior, and how to retrieve a job that outlives the wait.

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, front-loaded with what the tool does and immediately followed by a concrete usage example and the routing caveat. Every sentence adds information; only the '/v1' phrasing is slightly jargon-heavy.

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 10-parameter, nested-object, async image mutation with no output schema, the definition covers the core intent but leaves the agent guessing on return shape (image URL vs job_id), polling via carpe_image_status, and the semantics of most optional parameters. Adequate to start a call, not complete enough to use it confidently.

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 only 40% across 10 parameters, so the description needs to compensate and largely does not. It touches prompt and the 1–3 images constraint and hints that wait_seconds relates to the queued job, but model, quality, resolution, aspect_ratio, safe_mode, output_format, and the passthrough 'extra' object get no explanation.

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?

The description gives a specific verb plus resource ('Compose or edit') and constrains the input to '1–3 source images and a prompt', which is what separates it from the single-image carpe_image_edit sibling. It never names that sibling, but the arity constraint alone lets an agent pick correctly.

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?

The only routing guidance is 'Always on /v1 — no market arbitrates multi-edit', which tells the agent not to worry about market selection but not when to choose this tool over carpe_image_edit, carpe_image_generate, or carpe_image_upscale. There are no exclusions and no prerequisites stated.

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