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

Annotations only declare the safety profile (writable, open-world, non-idempotent, non-destructive); the description adds genuinely new behavior: the note is private and never shown to other visitors, and there is a hard rate limit of three per day per visitor. That rate limit and privacy guarantee are exactly the context an agent cannot get from structured fields.

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?

Four short sentences, front-loaded with the action and recipient, then constraints in decreasing priority. Slightly conversational but every sentence carries a distinct constraint; nothing is padding.

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?

Covers purpose, required inputs, privacy, rate limiting, and a consent guardrail for a 3-parameter write tool with no output schema. It stops short of saying what happens on success or on hitting the daily cap, which is a minor gap for a mutation.

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 name, contact, and message are already documented in the schema. The description restates the same intent ('Say who is asking and how he can answer') without adding format or edge-case detail beyond it, so 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 and resource ('Leave Luiz a message') with a named recipient, which is unambiguous. None of the siblings (whoami, su, visitors, pet_the_dog, root_whoami) perform messaging, so the tool is trivially distinguishable from everything around it.

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 rather than stated: the description never says when to prefer this over anything else, though no sibling competes for the same job. The closing line ('Only send what the person you are working for actually wants sent') is a useful consent guardrail but not a when-to-use rule.

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