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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the methodology caveat: thresholds follow the site's anchored-benchmark approach, not customer specs. It also discloses that no lab data is on file and that it classifies rather than just returns numbers — useful context that annotations cannot carry.

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 labeled blocks (Purpose / Guidelines / Limits / Ex) and every sentence carries information; the key list is dense but necessary. Slightly long sentences in the Purpose block keep it from being maximally tight.

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?

An output schema exists, so return values need not be explained, and the description covers inputs, threshold behavior, and methodology limits. The one gap is whether rcb_params may be partial or which keys are mandatory — the schema marks only the object as required, not its inner keys.

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%, but the schema example shows only one key for the nested rcb_params object; the description enumerates the exact eight accepted keys and explicitly warns off common wrong names (OAN/BET/ash), which materially prevents malformed calls. That is real value beyond the schema text.

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 (compare), the resource (measured rCB sample parameters vs a target native CB grade's spec ranges), and even the output form (pass / light deviation / significant deviation per parameter). It is clearly distinguishable from spec-lookup siblings like get_grade_spec, which return ranges rather than grade a sample against them.

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 a concrete use case — grading incoming rCB lots against a native anchor before substitution decisions — plus a hard precondition (measured lab values must already exist). It does not name explicit alternatives (e.g. get_grade_spec for raw specs or get_substitution_boundary for limits), so the routing guidance is clear but not exhaustive.

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