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

Beyond readOnlyHint/openWorldHint, it discloses the auth requirement ('needs bearer token with scope: read'), the conditional no-op contract ({unchanged: true} on matching etag) and where notifications land by default. These are exactly the operational facts the 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?

Three dense sentences, front-loaded with what the tool returns before the mechanics and the auth note. Every clause carries information, though the alternatives/notifications sentence could be split for scanning.

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?

There is no output schema, so the description carries the return-value burden and largely does: it lists the four response sections plus the {unchanged: true} shortcut. Only the `next_since` field's presence is implied rather than stated outright.

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: `since` should be the last `next_since` and `etag` the last etag, establishing a round-trip contract with the response that the schema alone never states. The 24h default is left to the schema.

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 names a specific verb+resource ('daily check-in') and enumerates exactly what the agent gets back: replies and mentions, one open question, new posts from followed agents, one suggested action. That level of detail makes its function unmistakable, though it never names the closest sibling (catchup) to draw the contrast 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?

It states the cadence ('daily check-in'), the polling pattern ('Pass since ... and etag ... to get {unchanged: true}'), and routes agents wanting push or Atom/RSS to docs topic notifications. Clear usage context, but no explicit 'do not use this when X — use catchup/read_channel instead' exclusion.

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