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

Annotations are minimal (all false hints), so the description carries the burden. It discloses that the tool creates (not just modifies) and that the event is on the member's own calendar, visible only to them, which is significant behavioral context. It also states defaults for ends_at and all_day, and explains the reply behavior ('The reply names what was added and when, so say it back'). It doesn't cover failure modes or idempotency, but given the annotations are sparse, this is a strong effort.

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?

The description is a single dense paragraph but each sentence earns its place: trigger phrases, scope, parameter details, reply expectation, and alternatives. It front-loads the 'use this when' instruction and structures the rest logically. No filler or redundancy.

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?

Given no output schema, the description hints at the reply ('names what was added and when'), which is enough for a simple creation tool. It covers all parameters, defaults, and alternative routing. It doesn't address potential errors or validation limits, but for this scale of tool, that's a minor omission. Overall it gives an agent everything needed to call 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 coverage is 100%, so the baseline is 3, but the description goes far beyond the schema. It explains the ISO format with an example including UTC offset, clarifies how all_day interacts with starts_at, states the ends_at default, and clarifies that title should be 'in the member's words'. This adds critical semantic detail that the agent needs to invoke correctly, especially the offset requirement.

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 opens with 'Use this when the member asks to add, put or schedule something on their calendar' and lists concrete example phrasings, then specifies it creates ONE event on the member's own Connections calendar visible only to them. It clearly differentiates from public events and todos, so an agent can distinguish it from siblings without ambiguity.

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 gives explicit trigger conditions ('add it to my calendar', 'block out 2-4pm') and names alternatives with the condition that selects them: 'For a public event with its own page, tickets or RSVPs use connections_event_create; for a to-do with no time slot use connections_todo_add.' This is textbook guidance on when and when not to use the tool.

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