inbox

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

With no annotations, the description carries the full burden; it usefully discloses pagination behavior ("If it says there are more, call it again"), which is real added value. It omits ordering, message format, whether reading consumes/marks messages, and any rate or auth constraints — gaps that matter for a pollable message queue.

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 tight sentences, front-loaded with the core action and followed by the pagination follow-up. The pronoun "it" in "If it says there are more" is slightly loose but costs little.

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 one-param read tool with no output schema, the description covers purpose and pagination but leaves the return shape and the meaning of 'poll mode' unexplained. Adequate, though an agent still has to discover the response format empirically.

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% with a single optional 'limit' param documented as "Max messages." The description adds nothing about limit semantics (e.g., default page size, interaction with the 'more' signal), so the baseline 3 applies.

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?

"Read messages sent to you" gives a specific verb plus resource and implicitly separates it from the write-oriented sibling 'send'. It does not explicitly name any sibling, but the read/inbox framing is distinctive enough that an agent can tell it apart from send, peers, and invite.

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?

"new ones in poll mode; recent history otherwise" hints at call context but never defines what 'poll mode' is or how an agent enters it, and no alternative tool is named for related tasks like replying or listing peers. 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.