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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds useful behavioral context: mode=count returns capped numbers, mode=flag returns booleans, and Mongo message archiving must be enabled. No contradiction with annotations.

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?

Three tight sentences with no filler: main purpose, endpoint, mode behavior, and deployment prerequisite. The essential information is front-loaded and every sentence earns 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 batch endpoint, the description, combined with annotations, covers the safety profile, endpoint, modes, and environment requirement. The absence of an output schema is partially mitigated by the explicit mode return types, though the exact response shape and keying are not described.

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 only 40% (appId and userIds are documented), so the description needs to compensate. It explains the mode semantics and hints at the cap behavior, but it leaves concurrency completely undocumented and does not clarify exactly what cap controls. Partial compensation only.

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 opens with a specific and precise action: 'Batch per-room unread message counts for a set of users', and reinforces it with the endpoint. It clearly differentiates this from sibling tools like history or message-search by focusing on unread counts and explicitly defining the two output modes.

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 clearly implies the use case and states a hard prerequisite ('Requires Mongo message archiving enabled'), but it never names alternative tools or explains when not to use this one. The agent must infer the tool's scope from the name and the description rather than being given explicit routing guidance.

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