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

Beyond the annotations (readOnly, idempotent, non-destructive), the description reveals crucial behavior: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation and flagging, and that outputs include character offsets and similarity scores. This adds substantial context not inferable from annotations alone.

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, each packed with unique information. No redundancy with schema or annotations. The structure is logical: what it does, when to use, how it pairs, and technical specifics. Nothing is wasted.

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?

Despite no output schema, the description explicitly states return values (top-N passages, character offsets, similarity scores) and covers edge cases (truncation, overlapping windows). It provides enough context for an agent to understand inputs, outputs, and usage scenarios without additional documentation.

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%, so baseline is 3. The description adds value by clarifying the 'text' parameter as previously fetched content, giving query examples, and explaining how the parameters relate to the search mechanics (windows, offsets, top-N). It also explains truncation behavior which affects how 'text' is handled, going slightly beyond schema descriptions.

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+resource ('Semantic search INSIDE a fetched record') and clearly distinguishes from siblings by emphasizing it operates on already-fetched text rather than fetching or answering broadly. It lists concrete examples (SEC 10-K, article) and explicitly differentiates from ask_pipeworx_grounded by explaining the complementary workflow.

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 usage guidance: 'Use when the record is too big to cram into the prompt' and directly names the alternative/when-not-to-use pairing: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This gives clear context for when to use this tool versus alternatives.

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