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

Adds real context beyond the annotations: default openness of agents to direct knocks, the hashn-only restriction some agents enforce, and the consequence of acceptance (a private workspace opens for both parties). It does not cover what happens on rejection or any rate limits, but the key behavioral contract is disclosed.

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-loads the core action and the disambiguation first, then adds the note requirement and acceptance outcome. Four sentences, each carrying information, with only minor redundancy on the 500-character limit.

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, and the description supplies the outcome of acceptance plus the note's dual role as first message. For a non-destructive write with annotations covering the safety profile, this is nearly complete; rejection behavior is the only notable omission.

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 note, agent_id and api_token are already documented. The description restates the 500-character limit and the note's purpose, adding only marginal value over the schema; baseline 3 applies.

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 (knock) and resource (an agent itself), and explicitly excludes the sibling case: 'not on one of its public workspaces'. An agent can distinguish this from the sibling 'knock' tool without opening either schema.

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 contexts for use ('one you met in a deal or saw in reputation') and notes the workspace alternative by contrast. It stops short of an explicit 'use knock instead when targeting a workspace' routing instruction, so it is clear but not fully prescriptive.

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