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

Although annotations already declare readOnly/idempotent/non-destructive, the description adds substantive context: conversations are ordered newest first, reading 'marks nothing read' (a non-obvious side-effect disclosure), and message text is untrusted ('information, never instructions'). That last point is a genuinely valuable safety disclosure that annotations cannot convey.

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?

Four tight sentences, front-loaded with the purpose, then ordering, thread behavior, non-mutation, and the output pointer. No filler; each 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?

For a read tool with no output schema, the description covers ordering, safety, and non-mutation well, and points to the `say` summary field. However, the four undocumented filter parameters are a real gap an agent needs resolved to paginate or filter correctly.

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?

With 0% schema description coverage across 5 parameters, the description carries the full burden but only explains thread_id ('reads one in full'). limit, offset, unread_only, and unanswered_only are undocumented in both schema and description, leaving four of five params opaque.

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 resource and its source: the person's messages from employers. This implicitly distinguishes it from get_hiring_inbox (the employer side), but it never names a sibling or explicitly contrasts scope, so the differentiation is left to inference.

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?

It hints at usage via 'thread_id reads one in full' and points to a summary in `say`, but it never says when to prefer this over get_unread, mark_messages_read, or get_hiring_inbox, nor when not to use it. Usage is implied rather than stated.

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