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

Annotations already signal readOnly, openWorld, idempotent, and non-destructive, but the description adds substantial beyond that: it reveals the refusal behavior with exact refusal_reason values, the success response shape, and the extra LLM call cost. No contradiction exists between the description and the 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 description is dense but every sentence earns its place: behavior definition, routing comparison, success/refusal contracts, use cases, and cost trade-off. It front-loads the primary purpose and then details, without repeating schema or annotation fields.

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?

For a complex meta-tool that routes across 5,724 tools, this description is complete: it defines the input (natural-language question), the process, the exact return contract with refusal reasons, and when to prefer the lighter sibling. No output schema exists, so the inline return and refusal shape are necessary and provided.

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%: every parameter, including all aliases, is already documented as equivalent to 'question' in natural language. The description adds no parameter-specific detail beyond the overall grounded-answer behavior, so the baseline-3 score applies because the schema does the heavy lifting.

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 mode ('Hallucination-resistant answer mode'), a clear resource ('high-stakes reads' via ask_pipeworx routing), and a distinctive behavior: extracting answers only from the tool result and refusing when data does not directly answer. It explicitly contrasts itself with ask_pipeworx by saying 'Same routing as ask_pipeworx' but then adding the extraction step, so the agent can tell them apart without opening schemas.

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,' followed by concrete examples. It also names the alternative and the trade-off: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.'

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