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

Even with readOnlyHint and openWorldHint in annotations, the description adds significant behavior: refusal reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), verbatim evidence extraction, confidence scoring, fetched_at, and an extra LLM call cost. This is exactly the transparency needed for a tool that an agent will trust with high-stakes answers. 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?

The three sentences are dense but efficient: they front-load the core purpose, then add return/refusal detail, use cases, and cost trade-off. Every clause contributes; only the full refusal enum could reasonably be deferred to an output schema.

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 supplies the full success return shape, the refusal shape with all enum values, the routing mechanism, and the cost/usage trade-offs. An agent has everything needed to invoke this tool correctly and interpret any response, including failures.

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?

All six parameters are aliases for the single required question, and the schema already provides full descriptions (100% coverage). The description adds only the context that the tool 'fills arguments' for the routed tool, which is helpful but doesn't change what the question parameter means or how it should be formed. 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 behavior ('Hallucination-resistant answer mode') and explains it routes like ask_pipeworx but only extracts answers from tool results. This clearly distinguishes it from ask_pipeworx and ask_pipeworx_beta, naming the exact mechanism that makes it grounded.

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?

Explicitly tells the agent when to use it: 'Use whenever an answer will be quoted, cited, or acted on' and when to avoid it: 'prefer ask_pipeworx for casual lookups.' It also surfaces the cost trade-off (one extra LLM call) so the agent can make a rational selection.

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