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

Even though annotations already declare readOnly, openWorld, idempotent, and non-destructive hints, the description adds meaningful behavioral detail: it only extracts from tool results, refuses when the data doesn't directly answer, and enumerates the exact refusal reasons. This does not contradict the annotations and gives the agent a clear contract for both success and failure.

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 well structured and front-loaded: mode definition, routing mechanism, return contract, refusal contract, then usage guidance. Every sentence contributes necessary decision-making or behavioral information, with no filler or redundant restatement of the tool name.

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?

The description is fully complete for this tool's complexity. Despite the absence of an output schema, it fully documents the success response and refusal response shapes. It also covers cost, use cases, and the distinction from a sibling tool, so an agent has everything it needs to invoke the tool correctly.

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 input schema has 100% description coverage: all parameters are aliases for question with clear explanations. The description adds no new parameter-level meaning, but none is necessary here because the schema already comprehensively documents the single required concept. Baseline 3 is appropriate.

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, differentiated purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It clearly identifies the resource (ask_pipeworx_grounded) and immediately contrasts it with ask_pipeworx, so an agent understands this is the grounded variant and not the casual lookup mode.

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?

The description explicitly states when to use this tool—'whenever an answer will be quoted, cited, or acted on'—and when to avoid it, recommending 'ask_pipeworx for casual lookups.' It also mentions the cost tradeoff of one extra LLM call, which is exactly the kind of decision guidance an agent needs.

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