create_mobile_brief

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

The description's "Synthesize" is consistent with readOnlyHint=true and idempotentHint=true, and "Missing motion and visual evidence stay explicit" usefully discloses that the output flags evidence gaps rather than fabricating. With annotations already covering the safety profile, the remaining gap is that nothing states whether the brief is persisted or returned, or what citations look like.

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?

Two tightly packed sentences with the core action front-loaded and no filler. The second sentence is compressed to the point of being slightly cryptic, but it still earns its place by describing gap handling.

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?

There is no output schema, so the description should convey the shape of the returned brief; it only hints at citations and explicit missing-evidence markers. Combined with five undocumented parameters, an agent knows the intent but not the full input contract.

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 0%, so the description carries the full burden, yet it only loosely maps "selected local references" to appIds and "flow evidence" to flowIds. The required goal, the platform enum (ios/android), and the constraints array with its 20-item cap go entirely unmentioned.

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?

"Synthesize a cited native-app direction" gives a specific verb and a concrete artifact, which is clearly a synthesis operation rather than a raw fetch or import. However, it never distinguishes itself from the sibling create_project_brief, leaving the agent to infer which brief type applies.

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?

"from selected local references and flow evidence" implicitly signals the prerequisite that appIds/flowIds must come from already-imported apps and flows, so usage context is inferable. But there is no explicit when-to-use, no mention of the alternative brief tool, and no statement of what happens when references are absent.

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