watch_activity

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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), but the description adds crucial context: it's a self-report, stale activity is displayed as unknown rather than assumed busy, and only watch_wait updates last_poll_at. This goes beyond annotations to clarify the tool's non-authoritative nature and freshness semantics.

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 concise sentences, front-loaded with the core purpose and immediately followed by usage and behavioral clarifications. No filler or redundant phrasing; every sentence adds value.

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?

Covers the main operational aspects: what it reports, when to use it, and its limitations. However, it does not describe the duty_id parameter or its expected format, which is required. For a simple tool with only two parameters, this is a minor gap but one that an agent might need to resolve.

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 0%, so the description must compensate. It lists the three possible values for the state parameter, matching the enum, but does not explain the duty_id parameter at all. While duty_id may be intuitive as a session identifier, the description leaves it undefined, which is a gap given the zero schema coverage.

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 clearly states the tool's function: 'Report this session's current activity' with explicit states (processing, waiting_user, idle). It distinguishes itself from siblings by noting that only watch_wait updates last_poll_at, positioning watch_activity as a self-reporting mechanism rather than a polling operation.

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?

Provides explicit when-to-use guidance: 'Use while working and after replying if waiting for input' and 'Refresh during long work when practical.' It also clarifies when not to rely on it: 'This is a self-report, not proof of polling' and 'Only watch_wait updates last_poll_at,' effectively routing the agent to the correct tool for polling updates.

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