visual_loop.status

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds some context: risk level 'read', maturity 'L1', and that session policy and approved output root requirements apply. However, it does not disclose what the returned status contains, whether it reflects a live loop or a stored snapshot, or what 'export additionally requires a committed snapshot' means for the caller. It adds modest value beyond annotations but leaves behavioral ambiguity.

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?

The description is a single compact sentence plus a short requirements list, with no filler. It front-loads the command identity and risk level. The requirements list is terse and information-dense, though the phrase 'export additionally requires a committed snapshot' is cryptic and could be clearer.

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 status-query tool with an output schema present, the description does not need to enumerate return fields, but it should clarify what a visual loop is, what status means in this harness, and how `loopId` relates to the loop lifecycle. The cryptic 'export additionally requires a committed snapshot' and the lack of any link to sibling loop tools leave an agent uncertain about prerequisites and interpretation. The output schema may help, but the description alone is not complete enough for correct invocation.

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 60%, with the only required parameter `loopId` having no description in the schema. The description does not explain what `loopId` refers to or how to obtain it, nor does it clarify the optional `_expectedSceneRevision` parameter. Since the description adds no parameter-level meaning, it does not compensate for the undocumented `loopId`; the baseline of 3 applies because the schema covers the underscore-prefixed harness parameters but leaves the core parameter unexplained.

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?

The description identifies the tool as a PartMe Blender Harness command named `visual_loop.status`, which implies it reports status of a visual loop, but it never explicitly states what the tool does (e.g., 'get the current status of a visual loop'). The name and title carry most of the meaning; the description focuses on risk, maturity, and requirements rather than the operation itself. It is distinguishable from siblings like blender_visual_loop_cancel or blender_visual_loop_create only by inference from the 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?

The description lists requirements ('Per-request argument checks and session policy still apply; Approved output root; export additionally requires a committed snapshot') but does not explain when to use this tool versus alternatives such as blender_visual_loop_record_capture, blender_visual_loop_record_verdict, or blender_job_status. There is no guidance on the context in which status should be queried, nor any exclusion of when not to use it.

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