Annotate Face

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

The description discloses persistence ('persists in the .FCStd as a JSON property bag', 'survives save/reopen'), update semantics ('re-using a name updates that annotation'), and the full return dict — all beyond the destructiveHint annotation. It accurately represents the mutation, and no contradiction exists.

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 longer than average but every sentence earns its place: purpose, persistence, integration, parameter details, return value. The parameter block is clearly delineated with 'handle:', 'face:', etc., and the return format is summarized in a compact dict notation. Minor redundancy with the title but 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?

Given no output schema, including the exact return dict is essential and done well. The description covers the tool's role, parameters, persistence, and return value. It doesn't mention potential errors or whether the updated document needs saving, but the persistence note implies it, and the destructiveHint covers the mutation risk. Complete enough for an agent to invoke correctly.

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 carries the full burden. It explains every parameter: handle, face (with allowed forms f_* tag, 'FaceN', or int index), role (with explicit enum values), name (with defaulting and update behavior), and meta (with example). This adds critical meaning beyond the bare schema.

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 opens with a specific verb and resource: 'Declare the semantic ROLE of a face — what it is FOR'. It clearly explains the purpose (intent-based editing) and differentiates itself from related tools by referencing check_airtight_path's downstream consumption. The title 'Annotate Face' is expanded, not just restated.

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 provides clear context: annotations are used 'so later edits can be checked against intent' and explicitly says 'Once declared, check_airtight_path accepts the role/name directly'. It doesn't explicitly mention when not to use it or alternatives like list_face_roles or declare_intent, but the downstream integration and persistence behavior imply the intended use case.

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