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

Goes well beyond the annotations (which only say non-readOnly, non-idempotent, non-destructive) by disclosing a concrete rate limit (max 5/day), the draft-policy branch, silent declines, the approval precondition, and exactly what the recipient sees in each reveal mode.

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 purpose then packs constraints, modes, and limits into one dense paragraph with no filler. Slightly long, but each clause carries actionable 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?

For a 5-param write tool with an output schema, the description covers the decision, side effects, limits, and policy branches that an agent needs. Return values are handled by the output schema, so nothing material is missing.

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?

Adds real meaning to the enum: identity surfaces name/handle/public links, context requires ≥40 chars and a specific content shape. message is noted as optional. shareStyle meaning is left to the schema, which already documents it, keeping this just short of 5.

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 ('someone from find_people'), and frames it as a 'first-contact request', which cleanly distinguishes it from siblings like find_people, list_knocks, and respond_knock.

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?

Clearly situates usage: the target is a ref from find_people, and it spells out the required reveal decision (identity vs context). It adds a precondition ('only with the person's approval of the wording') but does not explicitly state when to prefer this over alternatives such as other outreach tools.

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