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

Annotations cover readOnly/idempotent/non-destructive, and the description adds far more: refusal behavior with enumerated refusal_reason values, verbatim-evidence extraction constrained to tool result content, the success-versus-refusal response contract, and the extra LLM call cost. It also surfaces failure modes like data_truncated and no_tool_match that annotations cannot express. No contradiction with 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 sentences in a logical flow: definition, mechanics, return/refusal contract, and usage/cost tradeoff. Every sentence carries high-value information, and the key differentiator (hallucination-resistant grounded extraction) is front-loaded.

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 having no output schema, the description documents the exact success and refusal response shapes, enumerates the refusal reasons, and covers when to use versus avoid the tool. For a complex tool with automatic argument filling, nothing an agent needs to invoke it 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 coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema: it reveals the tool performs routing and 'fills arguments' automatically, so the agent only needs to supply a natural-language question rather than pre-resolving parameters. This tells the agent how to interact with the parameters in a way the schema alone does not.

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 definition: 'Hallucination-resistant answer mode for high-stakes reads' — a specific verb+resource with a distinctive attribute. It explicitly differentiates from siblings by stating it 'EXTRACTS the answer using ONLY what the tool result contains' while acknowledging the same routing as ask_pipeworx, so an agent can distinguish it without opening the 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?

Explicit when-to-use guidance is given: use whenever an answer will be quoted, cited, or acted on and facts must not be invented (financial verdicts, legal claims, medical lookups, public statements). It names the alternative and the exclusion: 'costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' Nothing is left to inference.

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