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

Annotations carry destructiveHint=true and readOnlyHint=false, and the description adds rich context beyond these: it bypasses the 7-day duplicate-invite rate limit (repeated calls harass people), cannot invite users who disabled invites or entered backoff, and mandates user confirmation before sending. This substantially explains the destructive nature flagged by the annotation.

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?

Structured with labeled sections (when-to-use, composition chain, policies) and front-loaded with purpose. It is long, but every section earns its place for a destructive tool — the rate-limit warning, exclusion rules, and confirmation requirement are all essential for safe use.

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 mutation tool with no output schema and 50% schema coverage, the description covers trigger conditions, alternatives, behavioral caveats, and verification path (check the row becomes SENT via get_activity_invites). Only the explicit return-value shape is unaddressed, but the verification chain largely compensates.

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 50% — activityRef is documented in the schema, but invitationId is not. The description's composition chain ('get_activity_invites selects speakers[].id → this tool') implies invitationId derives from get_activity_invites output, adding meaning to the otherwise undocumented parameter, though it doesn't explicitly label invitationId as speakers[].id.

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 states a specific verb+resource ('immediately send an invitation DM to a single roster candidate') and explicitly scopes it to one-at-a-time with 'deliberately no batch parameter.' It clearly distinguishes itself from set_guest_invite_plan, which handles batch/scheduled invites.

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?

Explicitly names the trigger condition ('user says invite this one now'), the exclusion case (to invite several people, use set_guest_invite_plan + set_guest_invite_plan_status(start)), and the composition chain with get_activity_invites. Nothing is left to inference.

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