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

Adds useful context beyond annotations: runs entirely in-process, no API key, and the limitation that it's not real embeddings. However, the claim about 'pipe-separated pairs' in batch mode is inconsistent with the schema's array-of-objects definition, creating a minor ambiguity.

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?

Four sentences deliver substantial information without redundancy. The core function is front-loaded, and the caveat about real embeddings is essential context. Slightly dense but all sentences earn their place.

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?

With an output schema present, the description adequately covers purpose, limitations, alternatives, and use cases. The only notable gap is the inconsistent batch-mode format description, which could confuse an agent about how to pass input.

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 already covers all parameters (100% coverage), so the description's mapping of 'bow', 'tfidf', 'ngram' to human-readable algorithm names adds value. The batch-mode explanation is helpful but the 'pipe-separated pairs' phrase conflicts with the schema's batch structure, slightly reducing clarity.

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+resource ('Compute text similarity') and enumerates the exact local algorithms (Bag of Words, TF-IDF, Character N-grams). It explicitly distinguishes from true embeddings by clarifying 'NOT real embeddings' and pointing to run_semantic_tests, which differentiates it from sibling 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?

Provides explicit contrast with run_semantic_tests for embedding-based similarity, noting no API key needed and in-process execution. Also lists concrete use cases (RAG retrieval testing, semantic search evaluation, text deduplication), making when-to-use clear.

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