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

Annotations already cover safety (readOnly, idempotent, non-destructive, open-world), and the description goes well beyond them: it discloses the extra LLM-call cost, the exact success payload shape, the full refusal_reason taxonomy, and even the refusal_cause sub-semantics for llm_error. The only gap is that it doesn't discuss latency, rate limits, or how 'data_truncated' is detected, which keeps it from a 5.

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 key differentiator (hallucination-resistant extraction) is front-loaded, followed by mechanics, return shape, and cost trade-off — a sensible order. It is dense and the refusal_reason enumeration is long, but each clause carries actionable information; a slightly tighter phrasing of the llm_error cause list would earn a 5.

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?

There is no output schema, so the description carries the full burden of describing return values — and it does, spelling out both the success object and every refusal variant including nested refusal_cause. For a high-stakes, single-question tool with 9 mostly-alias parameters, nothing an agent needs to call or interpret it is missing.

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 parameters are self-documenting aliases, so the baseline of 3 applies. The description adds routing context that implicitly explains why a question may be rewritten, but it never mentions the alias set or prefer_tool, so it contributes no meaning beyond the schema text.

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 names a specific verb and resource — an answer-extraction mode that routes to a tool and then extracts using ONLY the tool result — and explicitly frames it as 'Same routing as ask_pipeworx' while differing in extraction strictness. An agent can distinguish it from ask_pipeworx and ask_pipeworx_beta without opening any schema.

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 gives an explicit use trigger ('whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts') with concrete domains (financial verdicts, legal claims, medical lookups), plus an explicit when-not rule ('prefer ask_pipeworx for casual lookups') justified by cost. That is the full when/when-not/alternative triple.

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