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

Annotations already declare readOnly/openWorld/idempotent, so the bar for added context is high. The description goes well beyond by specifying the exact success return shape, the refusal rejection object with five concrete failure reasons, and the extra LLM call cost. This directly informs agent expectations about side effects, cost, and error modes.

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 clause earns its place: purpose, routing relation, extraction constraint, output contract, refusal semantics, use cases, and cost trade-off. It is front-loaded with the core purpose and then systematically builds behavioral detail without filler.

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 fully documents the return payload and refusal variants, so the agent knows what to expect. It also explains the routing behavior, the single-extra-call cost, and when to select the sibling. Nothing necessary for correct invocation or outcome interpretation 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?

The input schema covers 100% of parameters, including documenting all six aliases for the single required question parameter. The description adds no additional parameter-specific meaning, which is acceptable because the schema already carries the burden. A 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 precise verb-resource pairing: 'Hallucination-resistant answer mode for high-stakes reads.' It explicitly relates to ask_pipeworx while distinguishing itself by what it adds — grounded extraction and explicit refusal. An agent can distinguish it from the sibling tools immediately.

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 says exactly when to use it: 'whenever an answer will be quoted, cited, or acted on' and when not: 'prefer ask_pipeworx for casual lookups.' It also names the alternative tool and a cost-based exclusion criterion, leaving no ambiguity.

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