upload_file

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that arbitrary filesystem paths are rejected, but this is already encoded in the schema for workspace_filename ('Absolute paths, '..' segments and symlinks are rejected'), so it adds little beyond structured data. It does not disclose permissions, overwrite behavior, return value, error conditions, or any side effects of attaching a file. For a mutation tool, this is a significant gap.

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 two sentences with no filler. The primary action and resource are front-loaded, and the alternative input modes and rejection restriction are stated compactly. Every sentence earns its place; nothing is redundant.

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 mutation tool with no annotations and no output schema, the description is too thin to be considered complete. It covers the core action and input constraints but omits critical context for an agent deciding to call it: what happens on success (e.g., returned attachment object), what happens on overwrite/duplicate, permissions required, and behavior when both content_base64 and workspace_filename are given. The schema covers parameter formats but not operational behavior, leaving the agent to guess at consequences.

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% (every parameter has a description), so the baseline is 3. The description adds meaning by grouping content_base64 and workspace_filename as alternative modes, clarifying the 'or' relationship implied by the schema. However, it does not explain precedence if both are provided, size limits, or encoding details beyond what the schema already states. It adds marginal structure but no new semantic depth.

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 'Attach a file to a task,' a specific verb and resource that clearly identifies the tool's purpose. It also distinguishes two input modes (base64 or workspace file) and explicitly rejects arbitrary filesystem paths, which sets it apart from sibling tools like download_file or get_task_files without needing to open schemas.

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 the two acceptable ways to provide content (inline base64 or workspace-relative filename) and states a restriction ('Arbitrary filesystem paths are rejected'). However, it offers no explicit guidance on when to prefer this tool over alternatives, no exclusions, and no mention of prerequisites (e.g., task must exist). Usage is derivable from the purpose but not explicitly framed against sibling tools.

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