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

Beyond the readOnly/idempotent annotations, the description reveals important behavior: BGE-base-en embeddings, cosine over 500-char overlapping windows, and a 200K char cap with truncation flag. It also pre-announces output structure (offsets and similarity scores), adding context annotations don't capture.

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?

Three dense sentences cover purpose, use case, output format, pairing, and algorithm details without redundancy. The structure front-loads the core action ('Semantic search INSIDE a fetched record') and then layers usage and technical behavior.

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 adequately covers return values (passages with offsets and scores) and edge cases (truncation flag). It also situates the tool within a broader workflow, making it self-sufficient for an agent to invoke 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?

Input schema already thoroughly describes all three parameters (text, query, limit) with ranges and examples, so description adds limited new semantic detail. It does reinforce the 'text you already pulled' context, but that's more of a usage hint than additional parameter semantics.

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 'Semantic search INSIDE a fetched record' with concrete examples of text inputs and output ('top-N passages with character offsets and similarity scores'). This distinguishes it from broader search tools like ask_pipeworx by specifying the input is already fetched text.

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?

It provides explicit when-to-use guidance: 'Use when the record is too big to cram into the prompt' and names the complementary tool ask_pipeworx_grounded with a clear workflow: 'fetch with the gateway, ground over the relevant passages instead of the whole document.' This gives the agent solid decision-making criteria.

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