Complete an object to 3D

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

With zero annotations, the description carries the full disclosure burden and does it well: it reveals the call is asynchronous (POST → 202 {job_id}), prescribes polling via scene_job_wait, and — most valuably — warns that 'Output is GENERATED geometry' with an honesty envelope in the artifact meta.json, preventing an agent from presenting synthetic mesh as scan truth. Error cases (e.g., uid that is not a segmented object) are not covered, but every non-obvious behavioral trait an agent needs is disclosed.

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?

Roughly 40 words, front-loaded with the purpose and then the HTTP contract, follow-up, and output nature in order of use. Every clause carries information; the only weak spot is the cryptic 'broker-thread lane' fragment, which adds jargon without clear value to an agent.

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 tool with no annotations and no output schema, it covers the full lifecycle: invocation (POST /objects/<uid>/complete), async handshake (202 job_id), polling (scene_job_wait), and output handling (GENERATED geometry + honesty envelope in artifact meta.json). Gaps: it never names where scan_id/uid come from or which sibling retrieves the produced artifact (artifact_fetch), leaving that inference to the agent. Given the workflow indirection, that is a meaningful but small gap.

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?

The schema has 0% description coverage, so the description must compensate. It partially does: the endpoint '/objects/<uid>/complete' ties uid to the segmented-object identifier, and 'segmented object' gives both parameters purpose. However, scan_id is never explained — no guidance on how to obtain it or what relationship it must have with uid. That is marginal but real interpretive value.

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: 'SAM-3D-Objects mesh completion for a segmented object,' which distinguishes it from sibling tools like scene_segment or scene_object_variants. The concrete endpoint '/objects/<uid>/complete' and the 202 response further pin down exactly what the tool does.

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?

Explicitly routes the follow-up: 'Poll with scene_job_wait,' naming the sibling tool to call next. The phrase 'for a segmented object' implies the prerequisite workflow (segment first, then complete), and the async lane detail signals this is a job-style call. It does not explicitly name when-not-to-use alternatives, but the conditional workflow is clear.

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