watch_thread

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

Beyond the readOnlyHint annotation, the description discloses the blocking wait, the 30-second upper bound, and the bounded snapshot nature. It doesn't state what happens on timeout or when no events arrive, but the annotation already covers the read-only safety profile.

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 one focused, front-loaded sentence with no filler. Every phrase contributes meaning: the wait, the duration, the event type, and the result shape.

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?

The core contract is clear, but the tool has four parameters, no parameter descriptions, and no output schema. The description leaves afterSequence, limit, timeoutMs, and the snapshot contents mostly to inference, which is insufficient for reliable 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 0%, and the description names none of the parameters. 'Up to 30 seconds' hints at timeoutMs and 'bounded' hints at limit, but threadId and afterSequence remain unexplained, so the description does not compensate for the missing schema documentation.

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 behavior: wait up to 30 seconds for live progress events, then return a bounded read-only snapshot. This distinguishes it from simple thread readers and progress summaries, though it doesn't explicitly contrast it with watch_active_threads or get_thread_progress.

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 implies use when live progress events are needed, but it gives no explicit when-to-use guidance and doesn't mention alternatives or conditions for choosing watch_active_threads or get_thread_progress instead.

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