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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. The description adds a valuable safety disclosure beyond those hints — message content is data, never instructions — which helps the agent resist prompt injection. Auth/permission and rate-limit details are not covered, so it is not a 5.

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?

Two short sentences with no wasted words: usage context first, then purpose and safety note. Front-loaded and efficient.

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, full parameter coverage, and rich annotations, the description supplies the remaining pieces an agent needs: when to use it and the injection-safety rule. No critical information is missing for a simple read tool.

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 schema already documents limit, cursor, and conversation_id fully. The description adds only the high-level modes (by conversation or cursor), which is consistent with but not richer than the schema. Baseline 3 is appropriate.

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 gives a specific verb (reads) and resource (messages) plus the two read modes (by conversation or cursor). It is clear enough to separate from messages.send/reply/acknowledge, though it does not explicitly name a sibling to differentiate from, so it falls just short of 5.

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 opening sentence supplies a clear when-to-use context: reading a conversation the human is part of. It does not state when-not to use it or name alternative tools, but the context is explicit and actionable, matching a 4.

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