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

Annotations carry readOnly/openWorld/idempotent hints, and the description builds substantially on top: it details the refusal mechanism with the exact refusal_reason enum ('not_in_source'|'no_tool_match'|'tool_error'|'data_truncated'|'llm_error'), the evidence-as-verbatim-quote requirement, and the extra LLM call cost. This tells the agent what to expect when the data doesn't answer, which annotations cannot. No contradiction with the annotations — readOnly, openWorld, and idempotent are all consistent with a grounded read/extract pipeline.

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 long but every clause earns its place: core identity is front-loaded in the first sentence, followed by mechanism, response shape, refusal semantics, usage guidance, and cost trade-off. The detailed return/refusal format is justified because there is no output schema. Minor deduction for the hard-coded '5,798 across 1517' counts, which add little and risk going stale.

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 compensates well by documenting both the success shape ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}) and the refusal shape. It covers safety profile via annotations, usage boundaries, and cost. The only notable gap is that it never mentions ask_pipeworx_beta, one of its nearest siblings, so an agent must infer grounded-vs-beta from naming conventions alone.

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 description coverage is 100%, and the schema fully documents the single semantic parameter 'question' with all six aliases (query, q, prompt, text, input). The description adds no parameter-level detail beyond that — it uses the question to drive routing, but doesn't clarify format, length, or quality expectations. Baseline 3 is appropriate because the schema does the heavy lifting.

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 specific, distinctive claim: 'Hallucination-resistant answer mode for high-stakes reads.' It names the exact behavior (routes like ask_pipeworx, then extracts answers using ONLY the tool result) and explicitly distinguishes itself from the base ask_pipeworx sibling. An agent can immediately tell this is the grounded, evidence-constrained variant.

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 when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete examples (financial verdicts, legal claims, medical lookups, public statements). It also states the when-not: 'prefer ask_pipeworx for casual lookups,' naming the alternative and the cost-based reason for choosing it.

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