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

With no annotations, the description carries the transparency burden, and it delivers: it discloses the commit/versioning behavior ("edit is committed back to the SAME design_id"), the absence of bounds validation ("the caller owns the coordinates"), and a safe default ("The heavy background image is never moved unless you name its id"). It does not explicitly address reversibility or auth side effects, but the version-commit framing and risk warnings are substantial.

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 front-loaded with the core purpose and uses three short paragraphs, each earning its place: motivation, mechanism/commit semantics, and validation caveats. There is minor redundancy with the schema (e.g., commit/version details appear in both places), but the prose is efficient and readable for the tool's complexity.

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 mutating tool with no annotations and an output schema present, the description covers the key contextual gaps: when to use it, why it exists, how edits behave, what is not validated, and where to find input ids. It does not mention the closely related roastify_update_design_text for text-only cases, but the high parameter-level detail and output schema make the definition sufficiently complete for an agent to invoke it correctly.

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 86%, so the baseline is 3, but the description adds real parameter-level meaning beyond the schema: it tells the caller that coordinates are not validated and are the caller's responsibility, that the background image id should generally not be included, and that element ids/current geometry should be sourced from roastify_get_design_text. These are practical semantics an agent could not infer from the JSON schema alone.

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 opening sentence states a specific verb and resource: "Move a group of elements together and/or resize elements; commit a new version." It also differentiates itself from siblings by explicitly contrasting with add_design_element ("Nothing is validated against panel bounds here") and by describing the unique rigid-block relocking use case. An agent can distinguish this from the many design-manipulation siblings without opening the schema.

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 description gives a concrete triggering scenario ("a block of layered content ... drifts out of alignment"), explains that this tool relocks the block, and explicitly names an alternative: "unlike add_design_element." It also tells the caller to source ids from roastify_get_design_text. It does not, however, clarify when the related roastify_update_design_text would be preferred for text-only edits, so the guidance is strong but not fully exhaustive.

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