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

Annotations already declare readOnly/idempotent/non-destructive and openWorld; the description adds non-obvious behavioral context that the source 'may load referenced assets' (the openWorld risk) and that it 'does not update the active MCP session or write a project' (a state-effect nuance annotations can't express). These are genuine additions beyond the annotations, though permission/auth or performance characteristics are unaddressed.

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 the core action and return payload, then layers defaults, capability limits, and side-effect boundaries. It is dense but nearly every sentence carries distinct information; the return-field enumeration is somewhat redundant given an output schema exists.

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?

With an output schema present, the description need not explain return values, yet it still summarizes them, and it covers scope limits and non-mutation. A small gap remains: with zero required parameters it isn't stated what happens if neither `code` nor `file` is supplied and no prior capture exists, leaving a mildly ambiguous invocation path.

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 100%, so all three parameters are already documented, including the hosted-server caveat for `file` and the default for `feature_id`. The description reinforces the default-curve selection semantics but adds no format or constraint detail beyond the schema, so baseline 3 applies.

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 (evaluate/inspect) and resource (authored NURBS curve from kernelCAD code or file), and enumerates exactly what is returned (degree, knots/multiplicities, poles, weights, flags, parameter range). It also explicitly bounds scope away from geometry-derived B-rep edge/face NURBS and surface/blend extraction, so an agent can distinguish it from surface and inspection siblings.

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 clear selection behavior ('defaults to the last captured curve in that script; pass feature_id to choose one') and explicit exclusions ('surface extraction and blending are not supported', 'not exact geometry-derived B-rep'). It does not compare against the similarly named `inspect` or `evaluate_script` siblings, so the routing guidance is strong but not complete.

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