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

Annotations already mark readOnly, idempotent, openWorld, and non-destructive, but the description adds substantial behavioral detail: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flagging, and return fields (character offsets and similarity scores). This goes beyond what annotations alone provide, with no contradiction.

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 yet focused. Every sentence carries purpose: it states the action, gives use cases, explains the algorithm and limits, and situates the tool among siblings. It is front-loaded with the core purpose and does not waste words.

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?

For a tool with no output schema and moderate complexity, the description covers all critical aspects: what it does, when to use it, how it works under the hood, input constraints, output characteristics (passages with offsets and scores), and relationship to other tools. The agent receives enough context to invoke it correctly.

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 coverage is 100%, so baseline is 3. The description adds contextual meaning by specifying that 'text' is content already pulled (e.g., SEC 10-K body) and that 'query' is a natural-language question, with examples. It also clarifies the 'limit' parameter's purpose via 'top-N passages.' While the schema already documents constraints, the description enriches the practical understanding of each parameter.

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 tool's specific verb and resource: 'Semantic search INSIDE a fetched record.' It distinguishes itself from siblings like search_datasets by focusing on already-fetched text and from ask_pipeworx_grounded by acting as a companion rather than a replacement. The use case (search within a document too large for the prompt) is explicit.

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 provides explicit when-to-use guidance: 'Use when the record is too big to cram into the prompt.' It also contrasts with ask_pipeworx_grounded by explaining how they pair together, and it mentions the value of character offsets for verification. Alternatives and complementary tools are both identified.

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