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

Annotations already declare read-only, non-destructive, idempotent behavior; the description adds substantial context beyond that: timeout behavior with default and max 300 seconds, cursor continuity semantics, no replay without since, and the per-credential concurrency limit. This is exactly the behavioral detail an agent needs for a long-poll.

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 paragraph is dense but front-loaded with purpose, then moves through return behavior, cursor usage, filtering, rate limit, and alternative. Every sentence carries operational information without filler, and the information is ordered by importance.

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 long-poll tool with no output schema, the description covers the key behavioral contract: when it returns, timed_out, cursor continuity, and concurrency limits. It stops short of describing the full return payload (e.g., the shape of new feedback items) and omits proposal_id semantics, but is otherwise sufficient for correct 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?

The schema documents kinds, since, and timeout_s with 75% coverage, and the description reinforces their meaning (cursor pass-through, default both, 300s max). However, the required proposal_id parameter has no description in the schema and is not mentioned in the description, leaving a clear gap for the one required argument.

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 opens with a precise verb and resource: hold the call open until a page gets new feedback, enumerating rows, comments, and replies. It clearly describes a long-poll wait rather than a list operation, though it does not explicitly name sibling list_feedback as the alternative for reading existing feedback.

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 explains exactly when to use the tool (waiting for new items), how to continue waiting via the returned cursor, and what happens without since (starts from now, no replay). It also names the CLI watch command as the alternative for continuous watching and states the 3-wait per-credential limit.

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