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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds far more: the DATA-not-instruction safety rule, the requirement to show a reply before sending and only then set confirmed=true, the explicit-approval requirement before opening links or running suggested tools, and the reduced view without an account.

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-loaded with purpose and action map, then behaviour and safety, then the edge case. Every sentence carries information, though the safety paragraph is dense enough that a tighter phrasing could trim a line or two.

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 7-parameter, multi-action tool with no output schema, the description covers the full operation surface, the confirmation gate on replies, the safety posture, and the unauthenticated fallback — enough for an agent to call it correctly without extra context.

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 100%, so the schema documents each field, but the description still adds action-level meaning the schema lacks — that a reply lands in the same feedback thread, that dismiss/snooze 'puts one away', and that settings shows or changes email notices.

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 resource (messages from the Datailo team to this person) and enumerates every operation through the action values, including list/read/reply/dismiss/snooze/settings. An agent can distinguish this inbox tool from siblings like datailo_invoke or submit_feedback purely from the text.

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?

It specifies when each action applies (e.g., 'reply' only for a message that invites a reply, 'settings' to read or change email notices), states the unauthenticated case, and routes service-specific inboxes to datailo_invoke. It even gives the conversational trigger: when a `notifications` block appears, mention it in one sentence but keep the person's task first.

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