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

The annotations already declare readOnlyHint=false and destructiveHint=true, so the agent knows this is a mutating operation. The description contributes genuinely new behavioral context (notes are internal-only, surfaced in the team dashboard), but it says nothing about the destructive flag: whether notes overwrite existing notes, whether they can be edited or removed later, or whether any existing user data is affected. That silence around the one annotation an agent most needs explained keeps this at a 3.

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?

Two short sentences, front-loaded with the action and the audience, with no filler. Slight deduction because the parenthetical about dashboard visibility could be folded more tightly, but nothing is wasted.

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 two-parameter tool with no output schema this is close to adequate: purpose, audience, and durability scope are covered. However, an agent still lacks guidance on note content, on the implications of destructiveHint=true, and on what happens if a user_id does not resolve, which matters for a write operation.

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 only 50%: user_id is documented (app id preferred, or VibeAdmin id from list_users) but the note parameter carries no description beyond maxLength 2000. The description does not compensate by explaining what should go in the note, expected length, formatting, or whether existing notes are visible to the writer first; 'leave context for the next person' is thematic, not actionable parameter guidance.

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 uses a specific verb plus resource ('Record an internal note on a user') and immediately clarifies the artifact's visibility ('visible to your team in the dashboard'). That makes it clearly distinct from the read-side sibling get_user_notes, though it never names that sibling directly.

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?

The sentence 'Use it to leave context for the next person' implies the intended scenario (handoff/context notes) but gives no exclusions, prerequisites, or alternatives such as when to use update_user_metadata instead. Usage is suggested rather than specified.

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