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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral detail beyond these flags: returns top-N passages with character offsets and similarity scores, uses BGE-base-en embeddings with cosine similarity over 500-char overlapping windows, and caps input at 200K chars with truncation flagging. No contradiction with 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 longer than minimal but every sentence contributes: purpose, use case, pairing with sibling tool, and technical details. It is front-loaded with the core semantic search action, then explains why to use it, and ends with implementation specifics. No redundancy or filler.

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 bears responsibility for explaining return values, which it does explicitly: 'top-N passages with character offsets and similarity scores.' It also covers the full context: when to use, technical implementation, input limits, and integration with ask_pipeworx_grounded. This is a complete picture for a semantic search tool.

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 baseline is 3. The description adds value by giving concrete query examples ('supply-chain risk', 'fiscal year 2024 revenue'), clarifying the type of text expected (SEC 10-K, article, long tool result), and mentioning the 200K char limit. This goes beyond the schema descriptions and helps the agent craft appropriate inputs.

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 uses a specific verb ('semantic search') and resource ('a fetched record') with explicit scope ('INSIDE a fetched record'). It gives concrete examples (SEC 10-K body, article) and clearly differentiates from broader search tools by focusing on searching within already-fetched text, not external sources.

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 explicitly states when to use this tool: 'Use when the record is too big to cram into the prompt.' It also explains the tradeoff (saves context) and pairs with ask_pipeworx_grounded, describing the workflow: 'fetch with the gateway, ground over the relevant passages instead of the whole document.' This provides clear usage context and relationship to an alternative.

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