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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds meaningful behavioral details beyond these annotations: it tells the agent the comparison will be 'pillar by pillar' and produce a 'one-sentence verdict', which clarifies the operational output structure. It does not contradict any annotation, and the description goes beyond what annotations imply about behavior.

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 a single sentence of about 20 words, front-loaded with the core action ('Compare') and fully specifies scope, method, and output. Every clause adds value: the input range, the comparison style, and the verdict format. There is no filler or redundancy.

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?

Given the tool's moderate complexity (3 parameters, output schema present, rich annotations), the description is largely sufficient. It explains the core behavior and output, and the output schema can handle return details. The main gap is the lack of guidance on when to use this tool vs siblings, and it does not mention the optional metro/category parameters which might affect comparison context, but these are documented in the schema. Overall, it is complete enough for an agent to understand the tool's function.

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 input schema already provides descriptions for metro and category ('Optional metro slug selecting a shared ranking context'), so those parameters are covered. The description reinforces the range of the slugs array via 'two to four companies', directly mapping to the schema's minItems/maxItems constraints. However, it does not add further meaning to the optional metro/category parameters or explain the concept of 'pillar', leaving semantic coverage at the schema level with modest augmentation.

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 starts with a specific verb 'Compare' and identifies the resource as 'companies' (businesses), directly stating the action and scope. It explicitly specifies the input range ('two to four'), the comparison method ('side by side, pillar by pillar'), and the output format ('one-sentence verdict naming which pillar separates them'), making it clearly distinct from sibling tools like get_business_profile or get_rankings.

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 implies usage for comparative analysis ('Compare two to four companies') but gives no explicit guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or refer to sibling tools (e.g., use get_business_profile for a single company). Since context signals list siblings but the description offers no contrast, it provides only implied usage context.

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