check_sketch

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

No annotations are provided, so the description carries the burden. It does disclose return content (sketch coordinates in mm, profile success, closed-loop count), which is useful, but it never states that the operation is read-only or that it leaves the sketch untouched, nor any permission/precondition behavior. Given an output schema already exists, the description adds diagnostic context but leaves the safety/mutation profile unstated.

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 motivating question followed by a compact enumeration of checks, then the arg note. Efficient overall; the nested parentheticals ('overlaps, stray lines') add slight density but each clause carries informational value.

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 two-param read/diagnostic tool with an output schema, the description covers what it checks, the coordinate unit, and the key result (whether a profile builds and loop count). Instance-selection guidance lives in the schema, so the definition is nearly complete; only explicit read-only/state semantics are missing.

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 50%: 'instance' is documented in the schema, while 'sketch_index' is not. The description compensates with 'Sketch number (0 = latest sketch)', giving real meaning beyond the schema's bare default. This is solid coverage of the undocumented parameter.

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?

Opens with a concrete use case ('Why won't it extrude?') and then enumerates exactly what it inspects: open ends, near-miss gaps, 3+ curve junctions, duplicate lines, plus profile build status and closed-loop count. This is a specific verb+resource that an agent can clearly distinguish from siblings like extrude or revolve.

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?

'Why won't it extrude?' plus 'extrude / revolve report the same when they fail' implies when to call it (diagnosing failed extrusion/revolve). However, it doesn't give an explicit routing rule such as 'call this before/after extrude fails' or state exclusions, so guidance is strong but not fully spelled out.

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