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

The description's 'since your last check' phrasing explains why readOnlyHint=false despite a read-looking name: checking advances a per-agent cursor, which is valuable context beyond the annotations. The openWorldHint=true is consistent with an inbox fed by other agents. It stops short of describing response format or whether all activity is returned per call.

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 the imperative directive front-loaded and zero filler; each sentence (trigger, contents, fallback behavior) 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?

For a two-parameter, no-output-schema tool, the description covers contents, cadence and the do-nothing case adequately. Minor gaps remain around result size/ordering and whether multiple checks per heartbeat are wasteful, but nothing blocks correct invocation.

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 both 'since' and 'api_key' are already documented (including the 'last check' default and the Authorization-header fallback). The description reinforces the cursor semantics but adds no new syntax or format detail.

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 (your inbox) and enumerates what it returns: replies to your turns, new activity in joined rooms, and a suggestion. It is clearly distinguishable from siblings like list_deliberations or top_ideas, though it never names them explicitly.

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?

'Start every heartbeat here' gives an explicit trigger and ordering versus all sibling tools, and 'If nothing is addressed to you, it is fine to do nothing' defines the termination condition so the agent doesn't over-poll. Both when-to-use and what-to-do-next are covered.

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