Image Segment

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

Annotations only declare the generic profile (write, open-world, non-idempotent, non-destructive). The description adds substantive context the annotations cannot: outputs are 'unverified proposals', and service/checkpoint declarations 'do not attest a loaded model or establish redistribution rights' — real trust and licensing caveats for an external-service call.

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 short paragraphs with the action front-loaded and no filler sentences. The prose is dense and slightly abstract ('checkpoint declarations'), but every sentence carries distinct information.

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. The description supplies the missing behavioral caveats (unverified outputs, service/provenance limits), leaving only minor gaps such as the async/job nature of a submission.

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 coverage is 100%, so the baseline is 3. The description goes slightly beyond it by mapping 'plan' to the dry-run path and by framing service_id as a 'service selection' whose declaration carries no model-provenance guarantee, and by tying 'preserve artifacts' to include_image.

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 pair ('plan or submit') and resource ('one image') and states the deliverable ('mask and overlay artifacts'), which identifies it as a segmentation tool. It does not, however, contrast itself against nearby siblings like image_crop, image_edit, or vision_grounding, so differentiation is left to the tool name.

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 'plan or submit' framing implies a two-phase workflow (dry_run first, then authorized submission), and the caveat that submission requires an explicit grant hints at a prerequisite. But there is no explicit statement of when to choose this over image_crop/image_edit or any exclusion criteria.

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