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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety and side-effect behavior are covered. The description adds meaningful behavioral context by naming the scoring algorithm (TF-IDF) and clarifying that it works offline without embeddings or API calls, though it omits details like sort order or score range.

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 tight sentences with no filler. The core purpose and the key differentiator (no embeddings/API) are front-loaded.

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 full schema coverage, rich annotations, and an output schema, the description does not need to explain return values. It adequately explains the method and intended context, though it could briefly mention output ordering or tie-breaking behavior.

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 schema already documents 'query', 'chunks', and 'top_k' (including its default). The description adds no parameter-specific meaning beyond what the schema provides, so the baseline of 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 ('Rank'), resource ('array of text chunks'), and the scoring method ('TF-IDF'). The phrase 'without needing embeddings or an API' implicitly distinguishes it from sibling tools like embedding_similarity and vector_similarity.

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 gives a usage context ('Simulates retrieval ranking for RAG testing'), implying it is for testing rather than production retrieval. However, it never explicitly says when to use this versus alternatives such as bm25_score, embedding_similarity, or rerank_evaluate, nor does it state any exclusions.

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