Upload complaint/claim attachments

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

Annotations already include destructiveHint=false and readOnlyHint=false, but the description adds crucial context: it is a mutation requiring a confirmation token and user confirmation. It also explains the multipart action execution via server-provided action, which is a behavioral trait not in annotations. No contradictions.

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?

The description is three sentences, with the essential constraints front-loaded: what to upload, how, and the prerequisite token. Every sentence earns its place—no fluff. It also usefully clarifies that `values` is optional and copied verbatim.

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?

Given the tool's complexity (nested objects, mutation, token requirement) and that an output schema exists, the description covers the critical aspects: when to use, constraints, and prerequisite. It doesn't mention return behavior, but the output schema covers that. Minor gap: it doesn't state what happens if token is invalid or if multiple attachments fail, but that's not essential.

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 self-documents all parameters. The description adds minimal extra meaning beyond what the schema provides—it notes `files` are images and `values` carries extra typed form fields, but these are already described in the schema. It does not add syntax or format details beyond the schema. Baseline 3 would apply, but the drop to 2 reflects that the description's repetition of constraints (e.g., 'base64 data URLs, whitelisted image MIME types, max 10 MiB each') is redundant with the schema; it doesn't clarify ambiguity like which part_name to use.

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 states a specific verb ('Upload') and resource ('image attachments to a complaint/claim'), with concrete constraints (1-5 images, base64 data URLs, whitelisted MIME types, max 10 MiB each). It also references the context ('warranty claim from complaint_claims'), which distinguishes it from generic upload tools. This is clearly distinct from siblings like `prepare_mutation` or `mutate_list`.

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?

Explicitly states when to use: 'Use when the user needs to attach photos... to a claim or complaint.' It also specifies it is mutating and requires a one-time token from `prepare_mutation`, and mentions it is for complaint attachments. This gives clear selection criteria versus read-only siblings like `complaint_claims`.

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