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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses the refusal mechanism with specific reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), the restriction to only tool content, and the evidence-citing behavior. This is rich behavioral context that an agent needs to trust the output and handle failures.

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 dense but front-loaded with the core value proposition, then logically flows into process, return format, usage guidance, and trade-off. It earns its length, though a minor trim of redundant phrases like 'fills arguments' could tighten it further.

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 fully specifies the success and failure return shapes, including the refusal_reason enum. Combined with annotations and sibling context, the agent has everything needed to decide, invoke, and interpret results 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 schema covers 100% of parameters, with all six effectively being aliases for question and documented in the schema itself. The description adds no new parameter-level semantics beyond what is in the schema, so the baseline of 3 is appropriate.

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 a precise resource and behavior: 'Hallucination-resistant answer mode for high-stakes reads.' It clearly states the tool extracts answers using only tool results, and differentiates itself from the sibling ask_pipeworx by being the grounded, high-stakes variant. The verb 'EXTRACTS' plus the explicit return/refusal contract leaves no ambiguity about what it does.

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 says when to use the tool ('Use whenever an answer will be quoted, cited, or acted on...') and when to prefer the alternative ('prefer ask_pipeworx for casual lookups'). It also notes the performance trade-off ('Costs one extra LLM call'), giving the agent actionable routing rules relative to ask_pipeworx.

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