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

Annotations declare readOnlyHint=false and destructiveHint=true, and the description adds a side effect the annotations cannot express: 'the organizer is told.' That is the key behavioral fact for an agent deciding whether to send an RSVP. It stops short of saying the notification cannot be retracted or whether a later response overwrites the earlier one.

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?

Three short clauses: what it does, where to get inputs, and when to use it. Front-loaded with the action and side effect; no 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?

No output schema, so the description need not describe returns, and the notification side effect covers the main unknown. The residual gap is that irreversible/multi-mailbox behavior is left to the schema rather than the prose.

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 75% with the comment and account parameters self-documented and the response enum inline. The description adds provenance for event_id and account, telling the agent where those values come from rather than just their types.

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 set (accept / tentatively accept / decline), a specific resource (one Outlook meeting invite), and the scope limit (one), so it is trivially distinguishable from create_calendar_event, update_calendar_event, and get_calendar_events.

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 the prerequisite explicitly (get the event id and account from get_calendar_events, provider 'outlook') and an explicit when-to-use guard: 'Use only when the user asked for this response.' That is both an instruction and an exclusion against proactive RSVPing.

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