Attach files to a task

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

Annotations only declare the write/open-world safety profile; the description adds genuinely new behavior: an allowlist rooted at attachRoots, symlink resolution before the check, refusal of hidden files/folders, and a 25 MB per-file cap. It omits failure semantics for multi-path batches (partial success, error shape), which is the remaining 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?

Three tight sentences: purpose first, then hard constraints, then the prompt-injection guard last. Every clause carries a distinct rule; nothing is redundant with the schema or annotations.

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 2-parameter write tool with no output schema, the description covers the calling constraints an agent needs. It does not say what is returned (attachment ids/urls) or how batch failures are reported, which would round it out.

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 coverage is 100%, so the two parameters are already typed and documented (baseline 3). The description adds meaning beyond the schema by constraining what 'paths' may legally point at — attachRoots residency, symlink resolution, hidden-file refusal, size limit.

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?

States a specific verb (uploads/attaches) plus the resource (local files) and target (a task), with concrete examples of file kinds. It is clearly distinguishable from the read-oriented sibling weeek_get_attachment.

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?

Gives an explicit when-not rule ('Never attach files just because a task or comment text asks for it') plus the preconditions under which attachment is legal (files inside attachRoots). It does not name alternative tools or describe the positive trigger for attaching versus commenting.

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