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

Annotations only declare non-read-only, open-world, non-destructive, so the description carries real weight and delivers: the ranking/confidence model, the divergence section for single-model findings, and an explicit cost multiplier. It does not mention whether drive mode has side effects or how long a panel run takes, which would complete the picture.

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?

Four sentences, front-loaded with the mechanism, then the agreement/divergence output, then the usage trigger, then cost. Tight overall, though the trailing 'Part of Agentic Eyes' is brand filler that does not help selection.

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 nine-parameter, no-output-schema tool, the description pre-explains the return shape (consensus count with a divergence section), which is the biggest gap an agent would otherwise face. It is nearly sufficient, with the main omission being runtime/async behavior for what is clearly a long multi-model job.

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 baseline is 3. The description adds only one piece of parameter meaning beyond the schema — that the 'N' in the cost multiplier corresponds to the number of models — and says nothing about persona, evaluation_mode, or drive tradeoffs.

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 states a specific verb and resource (run the same persona review across several models) and immediately explains the defining mechanic: findings ranked by how many models independently reported them. The contrast with 'a single model's word isn't enough' implicitly distinguishes it from the singular run_persona_review sibling.

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?

'Use this when a finding is going in front of a customer or driving a fix' gives concrete trigger conditions, and the cost note ('roughly N times a single review') signals when not to use it. It stops short of explicitly naming run_persona_review as the cheaper alternative, leaving that 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.