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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description goes well beyond that by disclosing the credit requirement, the 1.2x fal markup, and the return payload (inline preview, public imageUrl, chargedCents). It does not cover failure modes, size limits, or latency, so not a 5.

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 tightly packed sentences: purpose and capability list first, input sourcing second, cost and return values last. No filler, no repetition of the title, and the most decision-relevant facts are front-loaded.

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 4-parameter paid mutation with no output schema, the description supplies the auth/cost context and describes the return payload, which is exactly what is missing from structured fields. Gaps remain around the undocumented 'preview' parameter and error/limit behavior, but an agent can invoke it correctly from this text.

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 only 25% (only 'prompt' is documented), so the description must compensate - and it does for the two image inputs, explaining that imageUrl accepts Picorn storage or Dropbox/Drive share links and that imageBase64 is the alternative. The 'preview' boolean is never explained, though the mention of an inline preview implies its role; prompt length/format is left to the schema.

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 ('Edit an existing picture') and then enumerates the concrete edit operations (retouch, change background, add/remove objects, restyle). The word 'existing' plus the underlying model name cleanly separates it from the sibling picorn_generate_image for creating new images.

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 implies the context of use (editing rather than generating) and states the precondition of a connected Picorn account with credits, but it never explicitly says when to pick this over picorn_generate_image or picorn_editor_* tools. No when-not guidance or named alternatives.

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