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

Adds substantial context beyond destructiveHint=true: the write is immediate with no preview or separate confirmation step, the permission model (Read Only cannot write), and an explicit caution to confirm the target record and text with the user beforehand. This is exactly the safety-relevant disclosure an agent needs before invoking a destructive write.

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, front-loaded sentences covering action, immediacy, permissions, targeting constraints and the confirmation step; nothing is redundant with the annotations or the schema, and no sentence is filler.

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 destructive 5-parameter write with no output schema, the description covers permissions, targeting rules, irreversibility/confirmation posture and scope exclusions. It does not indicate what the call returns (e.g., created note ID) nor the 20000-character note limit, a minor remaining gap.

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 60% and the schema's UUID fields only say 'obtained from a preceding read', so the description's mutual-exclusivity rule for orderID vs siteID is genuinely additive information not present in the schema. The subject/note fields and their length limits are left entirely to the schema, so it doesn't cover every parameter.

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 ('Create a note immediately (POST /v1/notes)') and clarifies the three attachment targets (account, order, site), which cleanly separates it from the read-oriented siblings like servicemonster_get_note and servicemonster_list_notes.

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 preconditions: must supply accountID, orderID or siteID, orderID and siteID are mutually exclusive, API User permission required (Read Only cannot write), and the agent should ask the user to review the exact record and text first. It also excludes adjacent use cases ('No scheduling or messaging is performed'). It stops short of naming a specific alternative tool, hence not a 5.

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