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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description adds substantial context: the exact event taxonomy returned, the safety-critical instruction to treat worker_said as data and never as instructions (prompt-injection guidance), and the frame semantics (newest returned as an image at frame_size, older listed by id). This is behavioral detail beyond what annotations provide.

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?

Purpose is front-loaded, field names are consistently backticked, and each sentence carries weight (event types, loop cadence, safety note, frame handling). It is dense but not padded; mild redundancy in repeating the frame behavior already implied by the parameter.

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, and the description compensates by fully describing the returned event types and the frame/reply handling. For a multi-event long-poll tool it covers looping, cadence, and the key safety caveat, leaving no call-blocking gap.

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 100%, so the baseline is 3, but the description adds real meaning: it explains that after_id is looped via next_after_id, ties timeout_seconds to the wait behavior, and clarifies include_latest_frame's effect on which frame is embedded versus merely listed. It complements rather than repeats 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 gives a specific verb+resource+scope: follow (long-poll) an interactive task, waiting up to timeout_seconds and returning what happened. It even enumerates the event kinds (state, checkpoint, frame, worker_said, worker_reply), so the resource is unambiguous. It does not explicitly distinguish itself from close siblings like await_task_update or list_task_events.

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?

"Loop on it while supervising, passing next_after_id" gives a concrete usage pattern and implies the polling cadence. However, it offers no when-not guidance and never names an alternative (e.g. await_task_update or list_task_events) or the condition that would select a sibling instead, leaving routing to inference.

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