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

Annotations already declare readOnly, idempotent, and openWorld. The description adds critical behavior: it refuses with structured reasons (not_in_source, no_tool_match, etc.), uses only tool-result content to prevent hallucination, and costs an extra LLM call. No contradiction with readOnlyHint.

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?

Each sentence earns its place: purpose, mechanism, return/refusal contract, usage, and cost tradeoff. Dense but front-loaded and 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?

For a grounded-QA tool with no output schema, the description fully specifies return shape and refusal contract, and gives selection guidance. Annotations plus schema cover safety and parameters, leaving nothing essential 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?

Schema description coverage is 100%; the schema documents question, timeout, context, and aliases (query/q, timeout_ms, etc.). The description adds no param-specific semantics, but this is not needed since the schema covers it. 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 names a specific verb+resource: 'Hallucination-resistant answer mode for high-stakes reads', and explicitly contrasts with ask_pipeworx by naming the same routing but a different extraction guarantee. It clearly differs from siblings like ask_pipeworx_beta by explaining grounded extraction and refusal behavior.

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?

Provides explicit when-to-use: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete domains (financial verdicts, legal claims, medical lookups, public statements). Also names the alternative and when to prefer it: '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.