bulk_invite_parents

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

With no annotations, the description carries the full disclosure burden. It explains that each unregistered guardian receives an email/text invite, that already-registered users are automatically skipped, and that the return message reports how many were actually notified. This is strong transparency, though it could also mention potential side effects like cost per message or rate limits, so a 4 is warranted.

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 organized with a clear lead, prerequisites, behavior, and input sourcing. It is slightly verbose in places (e.g., repeating 'from list_parents'), but it front-loads the purpose and keeps each sentence informative. The structure supports quick comprehension.

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 the tool's moderate complexity (2 params, output schema exists), the description covers all necessary aspects: purpose, prerequisites, behavioral nuance (skip logic, return count), and how to obtain valid inputs. The output schema is presumably available to detail the return format, so nothing critical is missing for an agent 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 0%, so the description must compensate. It adds meaningful context: `user_ids` are specifically the guardian IDs from `list_parents`, and the tool skips already-registered ones, making it clear that passing registered IDs is safe. While it doesn't delve into array size limits or type formats, it provides enough beyond the raw schema for correct invocation.

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 a clear, specific action: 'Send registration invitations to multiple guardians at once.' It identifies the resource (guardians) and distinguishes itself from the singular `invite_parent` sibling by emphasizing 'multiple' and 'at once.' The behavior of skipping registered users further clarifies its scope.

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 explicitly states a prerequisite (PS_ENABLE_WRITES) and provides a concrete workflow: obtain user_ids from `list_parents(school_id)`, typically those with `registered=false`, including the 'invite all' pattern. This is actionable guidance for when to use the tool and how to source inputs, clearly differentiating it from alternatives.

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