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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the bar is lower. Yet the description adds rich behavioral context: it reveals the embedding model (BGE-base-en), the windowing strategy (500-char overlapping windows), the similarity metric (cosine), and the 200K-char cap with truncation flagging. It also states the return format (top-N passages with character offsets and similarity scores), which gives the agent a clear expectation of side effects and output characteristics beyond the annotation hints.

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 three sentences, each earning its place: the first defines the mechanism and output, the second explains when to use and the pairing alternative, and the third gives technical implementation details. It is front-loaded with the core purpose and contains no filler or repetition. Every sentence provides distinct value, and the length is appropriate for the tool's complexity.

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 does the job of explaining what the agent will receive (top-N passages with offsets and similarity scores). It covers the operational constraints (200K cap, truncation), the technical approach (BGE, cosine, 500-char windows), and the intended use case (cramming large records). It also connects to a sibling tool. For a tool with 3 parameters and no output schema, this is fully complete.

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 all three parameters: text, query, and limit. The description adds context by clarifying that text is 'already pulled' and by giving query examples, but it does not add significant meaning beyond what the schema already provides. The 200K cap is also in the schema, and the limit bounds are in the schema. Thus, the description stays at the baseline 3, providing marginal additive value.

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 a precise action: 'Semantic search INSIDE a fetched record,' naming the specific resource (fetched text) and scope (inside that text, not fetching). It differentiates from siblings by explicitly positioning it as a focused search over user-supplied text, and even contrasts with ask_pipeworx_grounded by describing a pairing. The verb 'search' is specific and the examples (SEC 10-K, article) make the purpose immediately clear.

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 states a direct use case: 'Use when the record is too big to cram into the prompt.' It also explains how to use it in a workflow: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This gives both a trigger condition and an integration path, which is more than most tools provide.

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