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

With zero annotations, the description carries the full behavioral burden, and it delivers: it discloses the blocking long-poll nature, the 25s cap, the same-shape return either way, and the precise timeout end-state (empty messages, unchanged next_cursor). What's missing is any statement about side effects — notably whether waiting acks or otherwise mutates messages, which matters given sibling host.msg.ack exists.

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 dense sentences with zero waste. The core behavior and timeout constraint are front-loaded; the return-shape equivalence and timeout end-state follow; the usage context closes it out. Every clause 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?

Given no output schema and no annotations, the description adequately covers behavior (blocking, timeout, end-state) and return shape by cross-reference to host.msg.inbox with named fields (messages, next_cursor). Minor gaps remain: it doesn't specify whether waiting affects ack state (relevant given unread_only and host.msg.ack), but nothing blocks an agent from invoking it 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?

Schema coverage is 100%, so baseline 3 applies. The description adds modest context around cursor ('one past cursor arrives') and timeout_s ('elapses... max 25s'), but these details are largely restated in the schema. No significant new meaning is added beyond what the parameter descriptions already provide.

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 verb and resource: 'Long-poll for a new message until one past cursor arrives or timeout_s elapses.' It clearly distinguishes itself from sibling host.msg.inbox by framing this as the blocking/waiting variant, so an agent can tell them apart without opening either 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?

The phrase 'for a client with no polling loop of its own' gives clear context for when to choose this tool, and referencing host.msg.inbox implicitly identifies the alternative. However, it never explicitly says 'use host.msg.inbox instead if you poll periodically' — the exclusion is implied, not stated.

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