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

Annotations declare openWorldHint=false and destructiveHint=false but omit readOnlyHint, so the description should ideally clarify that this is a write/notification action. It does add value annotations lack by disclosing the required scope (desk.supervise). Still missing: whether the nudge is delivered in-app only, whether it is logged/visible in activity history, and whether the recipient must be online.

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?

One sentence with zero filler: action, object, recipient, and permission prerequisite all appear up front. Nothing is redundant with the title or repeated, and an agent can parse it in a single read.

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 four-parameter notification tool with full schema coverage and no output schema, the essentials are covered: what it does, who receives it, and the required authorization scope. Only minor gaps remain (delivery channel and whether the nudge is recorded), which are not strictly needed to invoke it correctly.

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 the schema already explains target_user_id, message, ticket_id, and purpose. The description's phrase 'supervisor coaching nudge message' merely mirrors the schema's wording for `message` and adds no format, length, or linking guidance (e.g., what ticket_id does to the nudge's context). Baseline 3 applies when the schema carries parameter meaning.

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 names a specific verb and resource: sends a 'supervisor coaching nudge' to a 'SautiDesk agent'. That is distinguishable from the generic messaging siblings (desk_send_dm, desk_send_message, desk_send_sms) by both intent (coaching/supervision) and audience (an agent, not a contact). It stops short of explicitly naming those siblings, so it lands at 4 rather than 5.

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 parenthetical '(requires desk.supervise)' gives a useful prerequisite for choosing this tool, which implies it is a supervisor-only operation. However, there is no explicit statement of when to use this versus desk_send_dm or desk_send_message, and no exclusion of cases (e.g., general agent messaging). Usage is inferred from the word 'coaching' rather than stated.

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