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

Beyond the annotations, the description discloses the asynchronous generation behavior by stating it 'Returns generation_id' and instructs the agent to poll status before fetching results. It also clarifies the exclusivity constraint without contradicting annotations. It does not discuss side effects on source assets or error conditions, but the 'replace' language combined with destructiveHint=false is not contradictory.

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?

Four short sentences deliver the outcome, source requirements, mode-to-parameter mapping, and lifecycle instructions with no filler. The most important constraint ('exactly one foreground source') appears early, and the follow-up flow is front-loaded before any less critical details.

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 tool with no output schema and six parameters, the description covers what is needed to invoke the tool correctly: source selection, mode mapping, required parameters, and the return/status/result workflow. It also notes the public HTTPS requirement for image URLs. An agent has enough context to understand both the call and the subsequent polling behavior.

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 schema already has 100% parameter coverage and describes each field individually. The description adds value by explaining cross-parameter relationships: exactly one foreground source must be chosen, and each backdrop_mode requires a specific supporting parameter. This is meaningful semantic information beyond the flat schema.

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 opens with a specific action, 'Remove or replace an image background,' and identifies the exact resource and path: 'Uwear's canonical free backdrop generation path.' This clearly distinguishes the tool from siblings like generate_avatar or upload_garment_from_public_url, which serve different purposes.

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 description gives explicit operational guidance: 'Provide exactly one foreground source' and maps each backdrop_mode to its required parameter. It also specifies the follow-up flow: 'poll get_generation_status, then fetch get_generation_results.' However, it does not name alternative tools or state when not to use this tool, so it stops short of a full 5.

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