upload_attachment

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

With no annotations provided, the description carries the full burden and discloses important behaviors: content_base64 is ignored if input_file is provided, and if filename/content_type are not given they are auto-detected. It also indicates an optional comment parameter. However, it does not mention side effects, permissions, size limits, or overwrite semantics, which would be valuable for a mutation tool.

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 opens with a one-sentence summary, then sensibly breaks down all parameters in a structured Args list. It is concise for the amount of information conveyed, though slightly verbose with parameter details that are necessary given the schema's lack of descriptions.

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 six parameters, two input modes, and no annotations, the description thoroughly covers how to correctly invoke the tool. It explains precedence rules, auto-detection behavior, and all parameter meanings. The existence of an output schema means return values need not be explained. The description is complete for effective use.

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 provides no descriptions (0% coverage), but the description's Args block explains every parameter, including the crucial relationships: content_base64 is ignored when input_file is given, filename is auto-detected, and content_type is auto-detected from filename. This adds meaning far beyond the schema's titles and property names.

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 'Upload a file as an attachment to a page' with a specific verb and resource, and distinguishes itself from siblings like download_attachment and upload_image_and_embed by focusing on general file attachments. It also explicitly names the two input modes (local file or base64), making the purpose unambiguous.

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 implies when to use this tool (for uploading attachments) but does not explicitly compare it with alternatives like upload_image_and_embed or download_attachment. It mentions the two input methods (local file vs base64) but lacks direct 'when to use this over X' guidance. The usage context is clear but exclusions are not stated.

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