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

Adds real context beyond the annotations (readOnly=false, idempotent=false, destructive=false): a 512 KiB inline cap, a screening/moderation step, a separate upload-link route, a returned attachment plus signed preview, and an explicit statement of no LLM or generation-credit cost. The non-idempotent hint is reinforced by the retry/verify advice. It stops short of describing collision or naming behavior.

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?

Front-loaded with the core action, then limit, return, scope, retry, and cost in five tight sentences; nothing is padded. A couple of fragments (e.g. 'scope:project applies to the project') are terse to the point of being telegraphic, keeping it short of a 5.

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 mutation tool with annotations, a full output schema, and complete parameter documentation, the description covers the operational essentials: size limits, alternative upload path, returned artifacts, scope semantics, and cost. Nothing critical is missing, though it could note whether re-adding the same file is rejected.

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 100%, so the schema already documents all seven parameters including the scope enum, MIME matching, and the base64 size cap. The description's scope and intent remarks largely restate what the schema says (e.g. shot only for images, intendedAtMs records intent), so it adds little beyond the baseline.

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+resource: stores and screens an image/video reference via the app attachment service. It loosely signals the sibling split by pointing at the 'app upload-link path' (studio_reference_upload_link) and the 'reference list' (studio_references_list), but does not name them explicitly, so differentiation is implied rather than certain.

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 a clear routing rule for the 512 KiB inline limit versus the larger-file upload-link path, and tells the agent to consult the reference list after uncertain replies to confirm persistence. No explicit when-not or named alternative tool, but the conditions are clear enough to act on.

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