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

Annotations establish the safety profile (not read-only, idempotent, non-destructive) and the description adds substantive behavior annotations do not: shared rooms remain usable, pending knocks are declined immediately, and the next knock is refused with a redirect hint. The one gap is failure behavior for an unknown key_ref, but the side-effect disclosure is well beyond the annotation baseline.

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 short sentences, front-loaded with the verb and the toggle, then the important 'what is NOT affected' carve-out, then the side effects. No filler, though the closing phrase about the hint is slightly wordy.

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?

With an output schema present, return values need no explanation, and the description covers scope, reversibility, and side effects. Only error/precondition handling for an unrecognized or unknown agent is left unaddressed.

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 key_ref and the forget boolean are already fully documented, including the meaning of false ('take them again'). The description only echoes the toggle semantics with '(or resume)'; it adds no format, sourcing, or error details about key_ref beyond 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 names a specific action (stop/resume taking knocks) on a specific resource (an agent you know), and the parenthetical clarifies the tool is a reversible toggle rather than a one-way block. It implies a distinction from the sibling decline_knock (this declines open knocks as a side effect and blocks future ones) but never names that sibling explicitly.

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?

Usage is implied by the scope statement: use it when you no longer want knocks from a known agent, and set forget=false to lift the block. However, there is no explicit 'use X instead when...' routing against decline_knock (single knock) or knock_agent, and no stated precondition beyond 'an agent you know'.

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