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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds genuine context beyond them: it explicitly disclaims that no upload or generation occurs, notes the 512 KiB inline limit rationale, and describes the downstream effect that uploaded results land in the project's reference list.

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 tight sentences with zero filler, and the core purpose is front-loaded before the limit caveat. Slightly more compact than strictly necessary but well structured.

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?

With an output schema present, return values need not be described, and annotations cover the safety profile. For a one-parameter read tool the description is complete, though a pointer to the actual upload sibling would close the remaining gap.

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?

The single projectId parameter is fully documented in the schema (100% coverage, including its source tools). The description adds nothing about the parameter, so the schema does the work and the baseline of 3 is appropriate.

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: 'Returns the app reference-upload screen for an editable project,' and scopes it with the 512 KiB inline-limit condition. It is distinguishable from sibling write tools like studio_reference_add, but it does not explicitly name which sibling is the alternative for actually performing an upload.

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 clause 'including for files over the 512 KiB inline limit' implies when this screen is useful, and 'No upload or generation occurs in this read' clarifies the boundary. However, it never states when to pick this over studio_media_upload_widget or studio_reference_add, so the routing guidance is only implied.

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