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

Beyond the readOnly/idempotent annotations, it discloses the blocking ceiling, early-return behavior, the timed_out return flag, and the no-minimum-interval retry policy — exactly the traits an agent needs. It omits error behavior (unknown conversation, bad token) which matters for a long-poll call.

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 sentences, no filler, front-loaded with the blocking behavior and immediately followed by the cursor rule and the retry rule. Every sentence carries decision-relevant information.

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 invocation mode, cursor handling, and the one return signal an agent must branch on (timed_out) despite no output schema. Minor gap: it says 'up to 25 seconds' while the schema declares a default of 20, which could mislead an agent about latency.

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%, so baseline would be 3, but the description adds real semantics: what it means to omit 'after' versus supply a cursor, and that the cursor comes from a prior read/wait. The wording 'pass next_cursor' for a parameter named 'after' is mildly confusing but resolvable from 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?

States a specific verb and resource ('holds the call open... returns as soon as a human reply arrives') and names the behavior it replaces ('so you do not need to poll'). That implicitly separates it from the read_messages/read_conversation siblings without needing to open their schemas.

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?

Gives concrete usage rules: omit 'after' for any unseen reply, pass the cursor for newer ones, and re-call immediately when timed_out=true. It does not explicitly say when to prefer a non-blocking read (read_messages) instead, so it stops short of full when-not guidance.

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