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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description goes beyond these by revealing the embedding model (BGE-base-en), windowing strategy (500-char overlapping windows), similarity metric (cosine), and a critical cap: 200K chars with truncation flagged. This is substantial added context about runtime behavior and limits.

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 well-organized: first sentence defines the core operation, second gives the use case and value proposition, third connects to a sibling, fourth details algorithm and constraints. Every sentence serves a purpose, with no fluff or repetition of schema fields.

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, the description covers inputs, return format (top-N passages with character offsets and similarity scores), an edge case (truncation over 200K chars with a flag), and the intended workflow alongside ask_pipeworx_grounded. This is sufficient for an agent to select and invoke the tool correctly without additional context.

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% with useful descriptions for text, limit, and query, including examples. The description adds extra semantic color by giving concrete text-source examples ('a SEC 10-K body, an article, a long tool result') and clarifying 'natural-language query,' which slightly goes beyond the schema. Baseline is 3; the added context justifies a 4.

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 a specific verb+resource: 'Semantic search INSIDE a fetched record.' It distinguishes itself from sibling tools by explicitly pairing with ask_pipeworx_grounded, positioning this as the 'search inside' step versus the grounding/response step. The scope and output (top-N passages with offsets and scores) are unambiguous.

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 when-to-use guidance: 'Use when the record is too big to cram into the prompt.' It also describes a concrete workflow with an alternative/companion tool ('Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document'), giving the agent clear decision logic.

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