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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses concrete behavioral details: embedding model (BGE-base-en), retrieval window size (500-char overlapping), similarity metric (cosine), character cap (200K), and truncation behavior (truncated and flagged). These are non-obvious traits that meaningfully affect tool invocation and output interpretation.

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 serving a distinct purpose: what it does, when to use it, and technical details. It is dense but not bloated; the technical sentence packs a lot of specifics while remaining readable. Slightly longer than strictly necessary, but every word contributes value.

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 carries the full burden of explaining return values, and it does: 'top-N passages with character offsets and similarity scores.' It also explains the search mechanism and constraints (200K cap, truncation). Combined with the clear use case and pairing guidance, the tool is fully understood from the description alone.

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 schema already provides 100% description coverage for all three parameters, so the baseline is 3. The description reinforces the meaning of 'text' (fetched record), 'query' (natural-language), and 'limit' (top-N) but does not add substantial new semantics beyond the schema. The example queries are a minor enhancement, not enough to raise the score.

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 clear, specific verb and resource: 'Semantic search INSIDE a fetched record.' It immediately distinguishes this tool from general search (search) and other siblings by scoping it to text already pulled, and specifies the output (top-N passages with offsets and scores). This is a textbook purpose statement.

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 it: 'Use when the record is too big to cram into the prompt' and explains the benefit (saves context). It also provides an explicit alternative pairing with ask_pipeworx_grounded, telling the agent how to use it together with another tool. This is strong usage guidance.

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