compare_answers

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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false. The description adds valuable execution-context behavior — that it runs locally and makes no provider calls — which is not captured by the annotations alone. No contradiction; it reinforces the non-destructive, side-effect-free nature.

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?

A single, front-loaded sentence that conveys purpose and a critical behavioral qualifier with no extraneous words.

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 simple two-parameter local comparison tool with safety-relevant annotations, the description covers what the tool does, its execution context, and its inputs via schema. The lack of an output schema is a minor gap, but 'summarize' conveys the nature of the result, so the definition is complete enough for selection and invocation.

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%, with both `question` and `answers` documented in the schema itself. The description adds no further parameter specifics beyond implying that answers are caller-provided, so the schema carries the semantic load.

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?

States a specific verb ('summarize'), a specific resource ('caller-provided answers'), and a key differentiator ('LOCALLY — does not call any provider'). This distinguishes it from the many sibling tools that invoke external providers (e.g., claude_request, gemini_request, validate_with_models). No ambiguity about the operation performed.

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 makes clear this is a local operation by emphasizing 'LOCALLY' and 'does not call any provider,' which tells an agent to choose it when comparing answers without external model calls. However, it does not explicitly name sibling alternatives or state when not to use it, leaving some inference to the agent.

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