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

The annotations already declare destructiveHint=false and idempotentHint=true, but the description independently explains the mechanism: check removes nothing, and ack 'stamps delivered_at, the row stays, NOTHING IS DELETED'. It also discloses the prerequisite that both parties must share a collection and that expiry defaults to 48 hours. This is exactly the extra context annotations cannot convey, and it is consistent with them.

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 definition is front-loaded with the identity of the tool, then action semantics, then the ack policy, then a shortcut — a logical order. Some of the action meanings (e.g. 'send: post to a teammate') duplicate the schema enum descriptions. The capitalized emphasis is deliberate policy signalling rather than padding, so it earns its place.

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 6-parameter, multi-mode tool with no output schema, the description covers what each action does and the key non-destruction guarantee. What is missing is the shape of a `check` result — whether it returns sender, collection, memory_ids, and timestamps — which an agent must know to act on it. Non-annotated prerequisites and semantics are otherwise well covered.

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 every parameter is already documented in the schema, including the action enum meanings and the recipient/collection/memory_ids roles. The description adds only the self-signal convention for agent_name and the shared-collection constraint, both of which are essentially restatements. Baseline 3 applies when the schema carries the parameter burden.

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 opening line defines the resource concretely ('sticky notes pointing at a memory_id') and the description then enumerates the three verbs (send/check/ack) that define the tool. An agent can tell this is a lightweight pointer-passing mechanism rather than a messaging tool. It stops short of a 5 because it never contrasts itself with the `message` sibling, which is the most likely confusion point.

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?

Unusually rich guidance: it specifies that a receipt or FYI is acked on read, that finished work is acked, and that deferred work or a peer's work is NOT acked with an explicit remedy ('say so in one line instead'). It also documents the self-signal handoff pattern and points to the memory_add/memory_edit shortcut. The gap is that it never says when to use signal versus `message` or `task_feed`.

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