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

While annotations already mark the tool as read-only, idempotent, and non-destructive, the description goes well beyond by disclosing exact refusal behavior with refusal_reason enum values (not_in_source, no_tool_match, tool_error, data_truncated, llm_error). It also reveals the evidence-quote extraction mechanism and the extra LLM call cost, which are not captured in annotations or schema. This is rich, actionable behavioral transparency with no contradiction.

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 longer than average, but every sentence contributes: purpose, routing behavior, success/refusal shape, use cases, and cost tradeoff. It is front-loaded with the core purpose and structured with clear success/refusal blocks. Slightly tighter wording could make it even more concise, but it is dense and well-organized rather than padded.

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 specifies the return shape on success ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}) and the refusal shape with all possible refusal_reason values. It also places the tool within its sibling context by naming ask_pipeworx and explaining the tradeoff. An agent has everything needed to select and invoke this tool 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 has 100% description coverage and explicitly documents that q, text, input, query, prompt, and question are all aliases for the same natural-language question. The description adds no additional parameter semantics beyond what the schema already provides, so the baseline of 3 is appropriate. There is no harm, but also no value added.

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 'Hallucination-resistant answer mode for high-stakes reads,' clearly identifying the verb (answer/extract), resource (Pipeworx tool routing), and its differentiator. It explicitly contrasts with ask_pipeworx by saying 'Same routing as ask_pipeworx' but 'EXTRACTS the answer using ONLY what the tool result contains,' making the distinction concrete. This lets an agent immediately understand what this tool does and how it differs from its closest sibling.

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?

Gives explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements).' It also gives the when-not-to-use alternative: 'prefer ask_pipeworx for casual lookups,' and even provides a cost-based rationale ('Costs one extra LLM call'). This is exemplary routing guidance.

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