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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds substantial behavioral details beyond that: it reveals the embedding model ('BGE-base-en embeddings + cosine over 500-char overlapping windows'), the character cap ('200K chars'), and the truncation behavior ('longer inputs are truncated and flagged'). It also clarifies the output structure (offsets and similarity scores), providing a transparent picture of what happens internally.

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 compact yet dense with critical information. It is front-loaded with the core purpose, then moves to usage context, a pairing recommendation, and technical details. Every sentence earns its place—no fluff or repetition. The structure naturally guides the reader from 'what' to 'when' to 'how.'

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?

Even without an output schema, the description fully explains what the agent can expect: 'top-N passages with character offsets and similarity scores.' It covers constraints (200K cap, truncation flag) and integration with a sibling tool. For a search utility, this provides all necessary context for the agent to use it correctly.

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 input schema covers all parameters with descriptions (100% coverage), so the baseline is 3. The description reinforces the schema by giving a natural-language example for 'query' and specifying the text input as 'text you already pulled.' However, it doesn't add meaning beyond what the schema already provides; the examples are helpful but not essential.

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 the tool's function: 'Semantic search INSIDE a fetched record.' It specifies the input (text + query), the output (top-N passages with offsets and similarity scores), and provides a concrete example (SEC 10-K body). It distinguishes itself from sibling tools by focusing on searching within an already-fetched text rather than general research or Q&A.

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 explains the benefit ('saves context, returns only the passages that matter') and even provides a pairing with ask_pipeworx_grounded, showing a clear workflow. This gives the agent strong guidance on when to invoke it over alternatives.

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