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

The description goes well beyond the annotations, which only state readOnly, idempotent, and non-destructive. It discloses the embedding model ('BGE-base-en embeddings'), the chunking method ('500-char overlapping windows'), the input limit ('cap is 200K chars (longer inputs are truncated and flagged)'), and the output includes character offsets for verification. No contradictions 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 concise yet information-dense. It opens with a clear verb-phrase, then contextualizes use cases, pairs with a sibling, and finishes with technical limitations. Every sentence serves a distinct purpose—no filler or repetition. The structure is logically ordered 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?

For a tool with no output schema, the description fully explains the return format (passages with offsets and scores). It also covers input constraints, the algorithm, and integration with ask_pipeworx_grounded, making the tool's capabilities and limitations clear. The agent can confidently select and invoke this tool 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 the baseline is 3. The schema already describes each parameter (e.g., text with 'max ~200K chars', query with example phrases). The description adds minimal param-specific meaning; it frames 'text' as 'the text you already pulled' and 'query' as 'a natural-language query,' but these are already implied in the schema. No significant added value beyond what the schema provides.

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 names the specific resource type ('a SEC 10-K body, an article, a long tool result') and the expected output ('top-N passages with character offsets and similarity scores'). This distinguishes it from sibling tools like ask_pipeworx or deep_research, which operate on broader 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?

Explicit guidance is provided: 'Use when the record is too big to cram into the prompt' and it explains the benefit ('saves context, returns only the passages that matter'). It also names an alternative/complementary tool: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This gives the agent clear decision criteria.

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