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

The description discloses the key side effect the annotations don't spell out: reading marks received messages as read, which is consistent with readOnlyHint=false and is exactly the mutation awareness an agent needs before calling. It also gives the pagination contract (50 a page), so the agent understands bounded returns.

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 short sentences with zero filler, front-loaded with the resource and page size, then the parameter mode, then the side effect. Every sentence carries distinct information.

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 no output schema, the description does the needed work by stating what comes back (newest messages, 50 per page) and how to page. It omits message field structure and ordering across conversations, which would matter for an agent parsing results.

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 100%, so the baseline is 3, but the description adds real meaning: 'with' switches to a single-conversation query, and '50 a page' explains why 'before' exists as a cursor. The api_key parameter is left to the schema, which covers it adequately.

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 the resource precisely ('your newest private messages, sent and received') with page size, which distinguishes it from send_private_message/reply and from read_lounge's public content. It stops short of naming a sibling, but an agent can tell what this returns 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?

'Pass with to read one conversation' gives an explicit mode switch that tells the agent how to move from a list view to a thread view. There is no explicit when-not guidance (e.g. vs read_lounge or post), but the context for using it is clear.

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