Attach Evidence File

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

Adds substantial context beyond the write/non-idempotent annotations: file bytes are read and uploaded server-side so they never enter model context, path resolution rules (relative/~ vs absolute), container mount behavior, refusal of paths leaving the tree, and hard constraints (PNG/JPEG, 5 MB max). This is exactly the kind of behavioral disclosure annotations cannot carry.

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?

Purpose and the key constraint are front-loaded, and each sentence carries real information. The embedded hard-coded example path (/Users/<user>/Projects/maestro-career-studio/...) is verbose filler that could be trimmed without loss.

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 5-param mutation with no output schema and 0% schema coverage, the description covers the file-handling dimension thoroughly but leaves the identity/placement params (proposal_id, step, label) and success behavior unexplained. Adequate but with clear gaps.

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 0%, so the description must compensate, and it does richly for file_path and the kind enum values. But proposal_id, step, and label — three of the four required params — are entirely undescribed in both schema and description, leaving half the call under-specified.

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+resource: attaching evidence from an image file already on disk. Clear what it does, though it never explicitly contrasts itself with the sibling attach_evidence (the non-file variant), so an agent must infer the split from the name alone.

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 concrete context for when this is used — a browser tool's saved screenshot reported by path — which sorts it from a generic evidence attach. However, it offers no explicit when-not or named alternative routing to attach_evidence.

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