Complete Unified Upload

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

The description discloses significant behavioral traits beyond the annotations: partial progress via null ETags, all non-null completion, selective field updates ('Send only the fields you intend to change'), defaulting of company_id and project_id, and specific failure modes (401/403/404). This is rich context that helps the agent predict side effects and errors.

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 a dense paragraph but every sentence contributes necessary operational detail, covering purpose, parameter rules, defaults, error handling, required parameters, and endpoint. It is not as tight as a two-sentence ideal, but its length is justified by the complexity of the multipart upload lifecycle.

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 nontrivial semantics, the description explains the success return ('Returns the modified complete unified upload'), common error payloads with status codes, defaults, and the resolution prerequisite. It is comprehensive for an agent to use the tool effectively in context.

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?

While the schema provides 100% field coverage, the descriptions are generic ('JSON request body field — the part etags'). The tool description adds crucial meaning: ETags must be one per segment in the same order as POST segments, null placeholders for not-yet-uploaded segments, and defaults for company_id and project_id. This goes far beyond the schema and fully compensates for its vagueness.

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 'Completes or updates progress for a unified upload', a specific verb+resource combination. It clarifies the operation with details like 'same order as POST segments' and the endpoint PATCH /rest/v2.1/.../uploads/{upload_id}, which distinguishes it from sibling tools such as create_unified_upload, get_unified_upload_status, or get_unified_upload_url.

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 clear context: part_etags come from PUT responses, order must match POST segments, and upload_id must reference an existing parent record to be resolved with a list tool first. However, it does not explicitly state when to use this tool versus alternatives or include any exclusions, so usage guidance is implied rather than direct.

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