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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, non-destructive), so the bar is lower, and the description adds genuinely non-obvious behavior: the 200K-char cap with truncation flagged, BGE-base-en embeddings with cosine over 500-char overlapping windows, and offsets enabling verbatim-quote verification. It stops short of a 5 only because how the truncation flag is represented and no-match behavior are left unspecified.

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?

Four sentences with zero waste: the core operation, the when-and-why, the companion-tool workflow, and implementation constraints each occupy one sentence. The purpose is front-loaded in the first sentence, and no sentence repeats what annotations or schema already provide.

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 correctly carries the burden of explaining return shape — top-N passages with character offsets and similarity scores — and adds windowing mechanics and truncation behavior. For a simple 3-parameter tool with full schema coverage, only edge-case behavior (no matches, exact truncation-flag representation) is missing, which is minor.

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% — text, query, and limit each have descriptions with defaults, ranges, and examples. The description adds only marginal context (what counts as a fetched record, why the 200K cap and windowing matter) without materially extending parameter semantics, so the high-coverage baseline of 3 is appropriate.

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 specific verb and resource — 'Semantic search INSIDE a fetched record' — and immediately distinguishes itself from fetching tools by requiring 'the text you already pulled.' It names the sibling ask_pipeworx_grounded and specifies its exact output (top-N passages with character offsets and similarity scores), so an agent can tell it apart without opening the schema.

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?

Explicit when-to-use guidance is present: 'Use when the record is too big to cram into the prompt,' with the reasoning that search_within saves context and returns only the passages that matter. It also routes around a specific sibling, describing the fetch-then-ground workflow with ask_pipeworx_grounded rather than searching the whole document.

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