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

Discloses critical behavioral traits beyond annotations: 4 MB size cap for inline content, allowed file types (images, PDF, text, CSV, Office, zip), and that company-level attachments have null app_url because they have no dedicated page. The annotations only indicate non-readonly, so this context is essential and well-covered.

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 dense but not bloated; every sentence adds value. It opens with the core action, then systematically covers content types, requirements, size caps, project optionality, allowed types, and return value. No filler or repetition.

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 complex tool with nested schema and multiple modes, the description covers all necessary aspects: attachment targets, mutual exclusivity, required fields, size thresholds, file type constraints, and the app_url nuance. Without an output schema, the mention of app_url and its null case is particularly valuable.

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?

Despite schema descriptions for individual fields, the description adds mutual exclusivity constraints, size limits, and clarifies that content_type is required only with content_base64. It also explains the semantics of project_id (omit for company-level) and the app_url return behavior, which are not fully captured in the 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 starts with a specific verb+resource+scope: 'Create an attachment on a company or one of its projects.' It clearly distinguishes this from sibling create tools (e.g., create_tasks, create_companys) by explicitly mentioning 'attachment' and its target scope.

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?

Provides explicit when-to-use vs when-not-to-use guidance: 'Provide exactly ONE of: text, content_base64, or link' and 'for larger files, upload to Drive and pass the URL as link instead.' It also clarifies when file_name is required and when project_id should be omitted.

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