Canonsheet

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

With no annotations, the description carries the full burden and does substantial work: it discloses the x402 payment flow, the 'Invalid arguments are refused before any payment' guarantee, the inclusion of negative prompts to prevent trait loss, and the reference-image behavior. It does not detail rate limits or persistence, but for a prompt-building tool these are significant and well-covered behaviors.

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?

The description is long but information-dense, with each sentence covering a distinct aspect: deliverables, model compatibility, face consistency, payment behavior, and validation. It is front-loaded with the core purpose before moving to edge-case behavior, and there is little fluff for the complexity it manages.

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 complex 8-parameter tool with nested objects and no output schema, the description covers the key operational facts: what is produced, how to keep faces consistent, how payment works, and that invalid input is rejected pre-billing. The only meaningful gap is the exact response format of the returned prompt set, but the description implies enough structure for an agent to proceed.

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 high at 88%, but the description adds structural meaning beyond the schema: appearance becomes the verbatim canon, traits trigger negative prompts, walk_axis produces a contact sheet, and has_reference defers the face to a reference image. This group-level semantics helps an agent assemble parameters correctly even where individual field descriptions are terse.

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 names a specific verb ('Build') and a specific resource ('a consistent prompt set for one human character'), then enumerates the exact deliverables: canonical image prompt, negative prompts, video prompt, and optional contact sheet. This level of specificity makes the tool's function unmistakable even without a sibling set.

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 provides clear context on when to use the tool: for consistent characters, for models that drop traits, and for reusing a canonical frame as a reference image. There are no explicit exclusions because there are no sibling alternatives, but the 'for the same FACE across images' guidance and the cross-model compatibility statement give an agent actionable direction.

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