upload_attachment

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, confirming it is a write operation. The description adds only the encoding requirement (base64), but fails to disclose that the file parameter also accepts absolute file paths per the schema. It does not discuss idempotency, side effects, or permissions, providing minimal behavioral insights beyond the annotations.

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 one sentence and efficiently conveys the core action. However, it omits important context (e.g., attachment association), so it is not supremely effective. It earns a 4 for being short and direct but could pack more value without sacrificing brevity.

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 (3 required parameters, no output schema, and a rich set of sibling tools), the description is insufficient. It does not explain what the attachment attaches to, any size/side effects, or how to retrieve the attachment ID after upload. The presence of sibling tools like get_attachment implies a workflow, but the description does not connect to it.

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?

With 100% schema description coverage, the schema already thoroughly documents all parameters. The description only mentions 'file as base64 encoded string', which underspecifies the file parameter (also accepts absolute path per schema) and adds no new meaning for code or filename. This actually introduces a potential misunderstanding.

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 clearly states the action as 'Upload a new attachment' with the specific requirement of providing the file as a base64 encoded string. This distinguishes it from sibling tools like get_attachment or delete_attachment, but it does not specify what the attachment is being attached to (e.g., project, case, run), leaving some ambiguity.

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 provides no guidance on when to use this tool versus alternatives like attach_external_issue or create_result. There is no mention of prerequisites, exclusion criteria, or context for its typical use, leaving the agent to infer usage from the tool name alone.

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