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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses that extraction uses only the tool result, that refusals return specific structured reasons, and that there is an extra LLM call cost. 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?

Every clause carries information: purpose, routing behavior, return/refusal contract, usage context, and cost trade-off. The description starts with the defining mode and the usage guidance is front-loaded before the cost caveat.

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 provides the complete response shape and the exact refusal reasons. It covers high-stakes decision rules and the alternative tool cost, making the tool callable correctly with the visible schema 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?

The schema already documents all parameters, so the baseline is met. The description adds the behavioral point that routing and argument filling are handled automatically, which reduces the agent's need to pre-select a sub-tool, though individual topic/query semantics still depend on the schema.

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 (answers via extraction) and resource (Pipeworx grounded) and states its purpose: hallucination-resistant reads for high-stakes use. It also distinguishes the mode from ask_pipeworx by the extraction-only constraint, so an agent can tell it apart.

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 explicitly says to use this mode when the answer will be quoted, cited, or acted on and facts must not be invented, and explicitly prefers ask_pipeworx for casual lookups because of the extra LLM call. This makes the selection condition unambiguous.

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