sculpt_compare

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

Annotations already indicate readOnlyHint and idempotentHint. The description adds valuable behavioral guarantees: 'deterministic,' 'existing capture and reference,' 'never launches a browser,' and 'never authorizes advancement.' This goes beyond the annotations and clarifies side effects and boundaries. No contradiction.

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?

Two succinct sentences. The first states the core function and scope; the second adds safety/behavioral boundaries. Every word earns its place, no repetition.

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?

The description covers purpose, safety, and general input semantics, but with no output schema it does not describe the structure or format of the 'diagnostic evidence' returned. It also leaves the region object details implicit. It is adequate for a simple read-only compare-like tool but not fully complete for an agent to invoke it with full confidence.

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 0%, so the description must compensate. It adds meaning by referring to 'capture and reference' (capturePath/referencePath) and 'normalized region' (regions), indicating existing inputs and normalized coordinates. However, it does not explain the id field inside regions, the default behavior of regions (global comparison when empty), or file path formats, leaving some gaps.

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 clearly identifies the action ('Produce deterministic diagnostic evidence') and the resources ('existing capture and reference'), and it distinguishes the tool from gate/plan siblings by noting it 'never authorizes advancement.' It stops short of explicitly saying 'compare,' though 'capture and reference' plus 'evidence' strongly imply it.

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 gives context: use when you need deterministic diagnostic evidence from existing captures/references, not for browser-based actions or advancing a gate. It provides exclusions ('never launches a browser,' 'never authorizes advancement') but does not name alternative sibling tools or explicitly state when this tool should be chosen over them.

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