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

Beyond the readOnly/idempotent annotations, the description discloses the core mechanism: routing across 5,798 tools, fetching data, extracting only from tool results, and returning either an evidence-backed answer or an explicit refusal with specific reason codes. It also reveals the cost behavior (one extra LLM call). This is rich behavioral disclosure well beyond the structured annotations.

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?

Four dense, purpose-driven sentences: purpose, mechanism, return/refusal contract, usage guidance, and cost tradeoff. Every sentence earns its place and the key differentiator ('grounded', 'ONLY what the tool result contains') is front-loaded. There is no redundant restatement of schema or annotations.

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?

With no output schema, the description fully compensates by specifying the success return shape and the refusal object with all refusal_reason values. It also covers operational context (routing scale, extra LLM call) and decision context (high-stakes vs casual). Nothing needed to select and invoke the tool correctly 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%, so the baseline is 3 and the schema already documents the question parameter and aliases. The description does not add parameter-level detail beyond contextual use-case examples (financial verdicts, legal claims), which are more about usage than semantics. The description neither improves nor harms parameter understanding.

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 states a specific, distinctive purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It clarifies it performs grounded extraction using only tool results, and explicitly differentiates it from ask_pipeworx by name. The agent can immediately tell this is a grounded/question-answering tool, not a general lookup.

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 explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts...' It also names the alternative and gives the condition to prefer it: 'prefer ask_pipeworx for casual lookups.' The tradeoff (extra LLM call) is clearly linked to the selection decision.

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