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

Goes well beyond readOnlyHint=true: discloses a fixed $0.001 cost per call even when nothing arrives, the immediate-return condition, the 25s cap on blocking, and the return shape (value null with timed_out true). It also flags a real security trait -- the box id is the only credential and anyone holding it can read, list, delete and wait -- which an agent must know before passing a box value.

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?

Front-loaded with the core behavior and return conditions before the box/credential detail, and almost every sentence carries non-redundant information. It is dense and the box discussion runs long relative to the operational contract, but nothing is filler.

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?

No output schema exists, yet the description documents the return contract (value plus timed_out, or an immediate value), the cost model, the timeout ceiling, and the credential/namespace model. An agent has everything needed to call it correctly and safely on the first attempt.

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 0%, so the description carries the full burden and does: `key` is what is watched for changes, `since` is the prior seq (0 = whatever is there), `timeout_seconds` is the block budget capped at 25, and `box` has three distinct semantics depending on whether it is omitted, a random string, or a box_... id. Every parameter gains meaning not present in the bare 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 ('Block until a key changes, then return it') and immediately reframes it as a long-poll rather than a subscription, which separates it from the non-blocking siblings like get/list. The added line 'This is how two agents sharing a box pass messages' makes the intent unambiguous.

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 selection logic -- pass the seq from the last value seen to get only newer ones, since 0 returns the current value, and the call returns immediately when seq is already ahead. It also spells out three box modes (omit, arbitrary random string for a shared channel, box_... id for a known box). It never explicitly contrasts with the sibling `get` ('use get if you don't want to block'), which keeps it below a 5.

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