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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses several non-obvious behaviors: 200K character truncation with flagging, BGE-base-en embeddings with cosine similarity, 500-char overlapping windows, and that results include character offsets and similarity scores. This gives the agent accurate expectations about output shape and limitations, and it contradicts no annotations.

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 dense but efficient: it leads with purpose, then usage context, then technical implementation details. Every sentence adds a new piece of information, though the middle section could be slightly tightened. It's not rambling or repetitive, earning a 4.

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 no output schema, the description correctly explains what is returned (top-N passages with offsets and similarity scores). It covers input requirements (200K cap), method (embeddings/cosine), and relationship to a sibling tool. Given the tool's complexity, the description is thorough and self-contained.

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 already covers 100% of parameters with descriptions. The description adds semantic richness: for 'text' it clarifies it should be a previously fetched record with examples, and for 'query' it provides natural-language query examples. It doesn't add detail to 'limit' beyond the schema's max/range, so a 4 is appropriate.

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 opens with 'Semantic search INSIDE a fetched record', giving a specific verb (search) and resource (the provided text). It distinguishes from siblings by emphasizing that the text is already pulled, as opposed to fetch-first tools like ask_pipeworx_grounded. The parenthetical examples (SEC 10-K, article, long tool result) further pin the purpose.

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?

It explicitly gives the use case: 'Use when the record is too big to cram into the prompt' and states that it 'saves context'. It also pairs with ask_pipeworx_grounded, indicating a complementary workflow. However, it doesn't explicitly state when NOT to use it (e.g., when the text is short or you need the whole document), so it's not a full 5.

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