compare

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

With no annotations, the description carries the full burden and does so well: it discloses the alignment rule (height/bottom alignment; scene scale irrelevant, proportions matter) and the exact text output (IoU score, per-height-band wider/narrower, missing/extra regions, key-height shift). It stops short of stating whether the operation is purely read-only or involves any cost, but the behavioral disclosure is unusually rich.

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-loads purpose before param details, with clear line-per-parameter structure. Dense and mostly earning its space, though slightly long and mixing prose justification with the parameter list rather than keeping them cleanly separated.

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 4-param tool with no annotations and no output schema, the description supplies the missing return semantics and alignment behavior, which is the critical gap. It lacks only an explicit read-only/mutation note and any guidance on choosing among the many sibling comparison tools.

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%, yet the description documents all four parameters: 'reference' syntax variants (path, path|N frame, path|0, path|x1,y1,x2,y2), 'render' expectations (same angle, orthographic preferred, transparent background for accuracy), all four 'mode' values with rendered layouts, and what 'method' controls. This fully compensates for the empty 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?

States a specific verb+resource: comparing a model render against a reference of the same angle, returning silhouette match % and divergence locations. It clarifies scope (silhouette/proportion comparison, not visual similarity) and anchors 'method' semantics to the sibling 'silhouette', so an agent can distinguish it from compare_views/compare_parts.

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 iterative workflow ('Правь модель и вызывай снова, пока совпадение не станет высоким') and defers 'method' behavior to the sibling silhouette. However, it never explicitly says when to choose this tool over compare_views or compare_parts, leaving the routing to inference.

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