compare_reference

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

With no annotations at all, the description carries the full burden and does well: it discloses the return payload (IoU, aspect difference, per-height corrections with a concrete example and world z) and the overlay image color semantics (red = only in reference, blue = only in model). It also bounds the method's validity (cannot verify absolute dimensions, apertures, attachments, materials, AAA fidelity). It does not explicitly state that the operation is non-mutating/read-only, which is the main remaining gap.

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?

Front-loaded with the core comparison and its normalization constraint, then returns, then the fix-and-recompare workflow, then caveats. Every sentence carries unique information (scope, outputs, next action, validity limits) 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?

No output schema exists, so the description must describe returns, and it does so concretely (IoU, aspect difference, per-height corrections, overlay image). Combined with 100% parameter schema coverage and explicit limitations, an agent has everything needed to call it and interpret results.

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 the baseline is 3; the description adds meaning by tying 'bands' to the returned per-height corrections ('at 70-80 % height...') and by telling the user to pair 'view' with the corresponding model view. That amplifies the schema beyond restatement, though it does not document each parameter exhaustively.

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+resource (compare the model's silhouette with a reference) and immediately narrows scope to 'proportions only (both normalised to their height)'. This is clearly distinguishable from siblings like review_model or analyze_quality, which serve different evaluation roles.

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 real workflow guidance: fix the listed bands via sibling edit_mesh (scale/soft_move on that z range) and compare again, plus prerequisites 'use corresponding reference/model views and separable backgrounds'. It also states what the tool cannot verify. It stops short of naming an explicit alternative tool for silhouette work, so it is strong but not exhaustive.

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