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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description goes beyond annotations by explaining return values (verdicts) and the requirement for an API key in embeddings mode, adding valuable behavioral context without contradictions.

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 concise and well-structured, with three sentences that front-load the core purpose and then add mode details and CI relevance. Every sentence contributes useful information without redundancy.

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?

Given the complexity (5 params, nested objects, output schema), the description covers key aspects: modes, API key requirement, default thresholds, verdict output, and CI use case. The existing output schema handles return-value details, so the description is sufficiently complete for an agent to select and invoke the tool.

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 the baseline is 3. The description adds some semantic context by mentioning 'tfidf (default)' and 'BYOK', but these are largely redundantly covered in the schema parameter descriptions. It does not meaningfully enhance parameter understanding beyond the schema.

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 defines the tool as a 'Semantic assertion primitive' that compares actual vs expected text pairs using cosine similarity and ROUGE-L. It distinguishes between tfidf and embeddings modes, and mentions returns of per-case and overall verdicts, which clearly differentiates it from generic similarity tools.

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 clear context for when to use each mode (tfidf is free/lexical, embeddings is true semantic with BYOK) and notes it is CI-ready. However, it does not explicitly name alternative sibling tools or state when not to use this tool, so it falls short of full exclusions.

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