ask_human

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

Discloses that the tool blocks until a reply or timeout, which is crucial for synchronous behavior. Also mentions the free-form nature and text reply. No annotations provided, but description covers key behavioral aspects.

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?

Two sentences that are concise and front-loaded with the primary action. The second sentence provides usage guidance. No unnecessary details.

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 covers purpose, usage, and blocking behavior, which is sufficient for a simple tool. It does not detail output format, but that is not critical for an interactive tool. Overall complete for its scope.

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 schema has two parameters: 'question' and 'context', but no descriptions are provided. The description does not explain the 'context' parameter, leaving its purpose ambiguous. The 'question' parameter is self-explanatory, but the lack of context explanation reduces clarity.

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?

Clearly states the tool asks a free-form question and waits for a text reply. Provides examples of use cases (preference, clarification, credentials, decision), distinguishing it from approval-specific tasks. The name and description align well.

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 states when to use the tool ('when you need information only a human can provide') with concrete examples. Does not explicitly contrast with the sibling tool 'request_approval', but the use cases are distinct. Slight room for improvement in naming the alternative.

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