job_attach

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

Annotations already declare the mutation/non-idempotent profile, but the description adds real value beyond them: append-only with no overwrite, and the side effect that images auto-record a screenshot event. That explains the non-idempotency and a hidden write the agent would otherwise not anticipate.

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?

Two short sentences, zero waste, with the core action front-loaded and the append-only constraint and side effect immediately after.

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?

With an output schema present and annotations covering the safety profile, the description supplies the key behavioral facts (append-only, image side effect). It is only slightly short on edge cases such as name collisions, file size limits, or failure behavior for a missing local path.

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 path and job_id are already documented in the schema with the same Mac-local framing. The description adds no detail on the optional `name` parameter (overriding the basename) and no format guidance beyond the schema, so the baseline 3 applies.

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?

Specific verb+resource: copies a local file into a job's artifacts, with the scope (MCP runs on the Mac) made explicit. It clearly distinguishes itself from add_evidence or write_addon_file by naming the destination as job artifacts, though it does not call out those siblings by name.

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?

Usage is implied rather than stated: attach a file to an existing job. There is no explicit when-to-use versus alternatives (add_evidence, job_link), nor any stated prerequisite that the job must already exist via job_enqueue.

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