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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds the key behavioral nuance that it returns 'Cites only' and does not emit verdicts, which is not present in annotations. This extra context clarifies the scope of results and avoids misinterpretation.

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 crisp sentences, no filler. The core action, scope, and explicit negative constraint are front-loaded. Every word contributes to decision-making, and the structure is highly scannable for an agent.

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 simple, single-parameter read-only tool, the description covers the essential behavior and output type (spec, Core source, GitHub cites) despite lacking an output schema. It does not discuss edge cases like pagination or formatting, but those are likely unnecessary given the tool's simplicity and annotation-based safety profile. The description is adequate for correct invocation.

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?

The input schema has 100% coverage for the single 'query' parameter, describing it as 'Spec section, rule, or implementation question.' The tool description adds only the synonym 'behavior' but no new format, constraints, or examples. Since the schema already fully documents the parameter, the description provides marginal added value, matching the baseline of 3.

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 states a specific verb ('Retrieve') with clear resources ('spec, Core source, and GitHub cites') and scope ('for a spec section or behavior'). It explicitly excludes verdicts, which distinguishes it from siblings like verify_claim or assess_argument. The purpose is unambiguous and differentiated.

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 provides a clear when-not: 'Does not emit aligned/gap/divergence verdicts,' which implies it is for citation retrieval, not analysis. However, it stops short of naming specific sibling tools as alternatives, so it lacks full explicit routing. This gives clear context without formal exclusions.

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