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

Although annotations declare the call non-read-only and idempotent, the description adds real context beyond them: the polling/idempotency contract via clientRequestId, that consent is persisted once per account, and that immutableUrl is an image-edit source rather than person-video consent. It does not state permissions required or what a completed check returns structurally, but the consent path is unusually well disclosed.

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?

Six short sentences, front-loaded with the selection rule followed by polling, then the consent branch. Nearly every sentence carries operational weight; the 'People are allowed in image edits' line is the one slightly orphaned statement, but it earns its place by clarifying a common source of refusal.

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 no output schema, the description does well to surface the key response concepts an agent must handle — a 'preparing' state, consentRequired, and immutableUrl. What's missing is any mention of terminal failure states or what to do if the reference is rejected, so the loop is not quite fully specified.

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 meaning of assetId, assetVersion and clientRequestId is already documented, and the baseline applies. The description adds only two small pieces of guidance — that ids/versions must be exact and that clientRequestId must be reused across polls — which are useful but not much beyond the schema's 'do not fabricate or normalize it' note.

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 description names a specific verb and resource: select an owned Brand Kit photo by exact Library id and updated_at, for use as an image-edit source. That distinguishes it from soclo_photo_reference_prepare and soclo_photo_reference_confirm, though the leading word 'Select' is slightly at odds with the title's 'Check', leaving a small ambiguity about whether it only reads state or also registers the reference.

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?

It gives concrete operating instructions — reuse the same clientRequestId while polling 'preparing', and if consentRequired is true, call soclo_photo_reference_confirm after showing a preview. It also excludes person-video consent and notes the generation quote is approved separately, which routes the agent away from adjacent tools. It does not, however, explain when to enter this tool versus preparing the reference first.

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