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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description doesn't need to. It adds real context beyond them: output preserves input order, all entries share the same field set, and no ranking or score is produced — which prevents an agent from misreading the result as ordered by quality.

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?

One sentence, front-loaded with the action and scope, closing with the key exclusion ('no score or ranking'). Nothing redundant.

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?

With an output schema present, return format needn't be explained; the description covers arity, ordering, field parity, and the non-ranking guarantee. Only minor gaps remain, such as behavior for unknown or duplicate facility identifiers.

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 coverage is 0%, so the description carries the burden for the single facilities parameter. It supplies the min/max count and, importantly, the semantic that input order determines output order — meaning the schema's minItems/maxItems alone cannot convey.

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 and resource (put facilities side by side), the exact arity (2 to 4), and the scope (same public record fields, no ranking). This clearly separates it from get_facility (single) and search_facilities (finding), so an agent can pick it without opening the schema.

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 phrase 'No score or ranking' implies when this is preferable to a ranked search, but no sibling tool is named and no precondition (e.g. valid facility IDs, existence checks) is given. Usage is inferable rather than stated.

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