buzz_unread

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

With no annotations, the description carries the full burden and does well: it explicitly states 'Read-only' and 'performs no writes', and discloses the heuristic nature ('NOT real read-state'), which implies it does not modify state. It does not cover output format or potential rate limits, but for a simple read-only tool these are minor omissions.

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?

The description is two sentences with no filler. The opening phrase 'Read-only activity digest' immediately communicates the core purpose, and each subsequent clause adds necessary detail (scope, heuristic warning, no-writes guarantee). Every sentence 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 tool with one optional parameter and no output schema, the description is reasonably complete. It explains what it counts (messages and mentions), the scope (channels and DMs), the default look-back, and the non-mutating behavior. It does not detail the exact return structure, but the description's conceptual output ('how many @mention you') gives enough context for an agent to expect counts.

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% (the 'hours' parameter has a description with default 24). The description adds marginal value by tying 'hours' to the look-back window ('last `hours`, default 24'), but this is essentially echoing the schema. No additional semantic detail like range or format is provided, so a baseline 3 is appropriate.

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 states a specific verb and resource: 'count recent messages from others' across 'channels and DMs', clearly distinguishing it from read/write siblings like buzz_read or buzz_post. It also immediately labels itself as a 'read-only activity digest', leaving no ambiguity about its function.

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 description provides clear context: it is for checking recent activity (messages and mentions) with a configurable look-back window. It explicitly warns it is 'NOT real read-state', which effectively tells the agent not to rely on it for accurate read/unread state. However, it does not name alternative tools (e.g., buzz_read) or give explicit when-to-use vs when-not-to-use conditions beyond that limitation.

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