compare_profiles

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

Annotations already indicate the tool is not read-only (readOnlyHint=false), idempotent (idempotentHint=true), and non-destructive (destructiveHint=false). The description adds the behavioral trait 'bounded' and the fact that it 'store[s]' evidence, which aligns with the non-read-only annotation. However, it does not explain what 'bounded' means or detail any side effects beyond storage, so transparency is moderate.

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?

The description is a single concise sentence that front-loads the core purpose and outcome. Every word contributes meaning, and there is no fluff or repetition. It is well-structured and easy to parse.

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?

While an output schema exists (covering return values), the description is incomplete for a tool that stores evidence. It does not clarify what 'bounded' means, where evidence is stored, or whether existing evidence is overwritten. It also fails to differentiate from compare_benchmarks, which is a significant contextual gap given the sibling tools.

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 schema has 0% description coverage, and the tool description does not compensate. It mentions 'two stored analyses' which loosely maps to baseline_analysis_id and candidate_analysis_id, but it does not explain the meaning of minimum_delta_percent or how these parameters interact. The agent would have limited understanding of the parameter values' roles.

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 states the action ('Compare two stored analyses') and the outcome ('store bounded profile-difference evidence'). It is specific to profiles, distinguishing it from sibling tools like compare_benchmarks, which likely compares benchmarks. The verb+resource combination is unambiguous and informative.

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 no guidance on when to use this tool versus alternatives. It does not explicitly name compare_benchmarks or any other sibling tool, nor does it specify conditions like 'use when you need to identify differences between profiles'. The only implied context is that two stored analyses are required, but no exclusions or alternatives are mentioned.

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