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

Beyond the readOnly/idempotent/destructive annotations, the description discloses that each agent is queried individually, the same question set is applied to every agent, and the output intentionally highlights disagreements. It does not detail output format or errors, but annotations already cover the safety profile.

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 front-loaded with the action and resource, then lists the concrete questions each agent is asked. It is a little wordy, but each sentence contributes useful decision context, and the closing note about disagreements earning its place.

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 read-only comparison tool, the description covers purpose, scope, question criteria, and core output behavior even without an output schema. The main minor gap is the mismatch between the description's 'two or three' and the schema's minimum of one agent, plus the unstated exact return shape.

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%, so the description adds little parameter-specific value. It reinforces the two-to-three agent intent, but it does not clarify behavior when the schema permits a single agent, which is a slight gap.

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 clearly states that the tool places two or three agents side by side and answers the same buyer-oriented questions for each. It distinguishes compare_agents from sibling tools by emphasizing side-by-side comparison and explicitly noting there is no combined score.

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 gives clear context: use this tool when evaluating agents before awarding a spend cap, and want to see disagreements rather than an aggregate. It does not explicitly name alternatives or say when not to use the tool, but the intended use case is well implied.

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