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

Annotations declare a non-readonly, non-destructive, non-idempotent, closed-world mutation, so the safety profile is already covered. The description adds genuinely new behavioral context: the call returns an async job that must be polled, and STEP/STP requires a follow-up face-selection step. It omits permission/auth requirements and what happens on duplicate imports, but adds real value beyond the annotations.

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 short sentences, front-loaded with the core action and then the prerequisite and follow-up flow. Every clause earns its place with no filler.

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?

An output schema exists so return values needn't be restated, and annotations cover the safety profile. The description completes the picture with the job-polling workflow and face-selection step. Only minor gaps remain (workspace_id meaning, auth, duplicate handling) for a 2-parameter mutation.

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 0%, so both parameters rely on the description. It usefully explains where upload_id comes from (list_uploads) and ties it to the import target, but says nothing about workspace_id or the expected ID formats. Partial compensation for the coverage gap warrants a 3.

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 and resource ('Import a file already uploaded to this workspace') and constrains scope to already-uploaded files, which cleanly separates it from load_sample or list_uploads. It also names the supported format (STEP/STP), so an agent knows what it produces a part/job from. It stops short of explicitly differentiating itself from every sibling, but the scope qualifier does most of that work.

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 prerequisite chain: obtain upload_id from list_uploads, and for STEP/STP poll the returned job with get_job(kind='step') before inspecting and selecting faces. That is concrete when-to-use and next-step guidance. It does not state exclusions (e.g., what to do for non-STEP formats or when not to import), so it falls short of a full routing rule set.

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