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

Annotations already cover the read-only safety profile, so the description's value-add is real: it discloses the time window ('this week's'), the coverage limitation ('only the channels the user switched on'), the ordering ('newest first'), and what each item carries. It does not address rate limits or pagination, but it adds substantive behavioral context beyond the annotations.

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 front-loaded sentences with no filler; the qualifying definition comes first, then the returned fields and coverage caveat. 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?

With no output schema, the description usefully enumerates the returned fields (kind, author, channel, message, when, reply count, link) and bounds the result set by time window and enabled channels. An agent has everything needed to invoke 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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to compensate for and nothing it is missing.

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 gives a specific verb+resource ('Slack conversations whose latest message waits on the user') and precisely defines the qualifying cases (DM, @mention, reply in a thread they wrote in). This distinguishes it from search_slack_messages and get_slack_thread without needing to open 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 scope ('this week's', 'channels the user switched on and their DMs') implicitly tells the agent this is a bounded triage view rather than a general search. However, it never names or contrasts with obvious alternatives like mail_waiting_on_me or what_needs_attention, so the when-to-use-vs-alternative guidance is only implied.

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