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

Goes beyond the annotations by disclosing that the result is a new, unsaved design the person can edit, that validation problems come back with path and fix, and that dryRun reports without creating a link. Annotations only carry the generic non-destructive/not-idempotent profile, so this adds real behavioral value.

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 sentences, front-loaded with the core action and return value, then sibling routing. Slightly dense with parentheticals but every sentence carries information an agent needs.

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?

No output schema exists, yet the description covers the return (an App Builder link) and error shape, plus both boolean flags and the composition source. The only thin spot is what the format mode actually emits, a minor gap for a 3-param tool.

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?

Adds meaning beyond the 67%-covered schema: it explains dryRun ('checks without making a link') and format ('format: true returns the format'), while composition's structure is documented in the schema itself. It stops short of fully defining the format-mode output, but the two behavioral flags are well clarified.

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 ('design a single screen', 'send one screen ... get back a link') and explicitly contrasts itself with the sibling propose_app ('For a whole app with navigation, propose_app is the matching tool'), so an agent can separate them without opening schemas.

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?

Gives clear context for when to reach for this tool (single screen in the Composition format that add_screen builds from) and names the alternative for the whole-app case. It lacks explicit when-not-to-use conditions beyond that sibling pointer, but the routing guidance is solid.

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