Invite a co-parent / partner / grandparent to share this household. They receive a one-time invite link by email; on accept, they join the household and can see all kids + saves.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, description discloses invite delivery (email, one-time link) and access granted (see all kids + saves). Good coverage of behavioral outcome, though could mention expiration or limits.
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?
Two sentences, no redundant information. Efficiently communicates purpose, mechanism, and outcome.
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?
Adequate for a simple trigger action with one parameter and no output schema. Explains process but lacks error scenarios (e.g., invalid email, already a member).
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?
Only one parameter (email) with 0% schema description coverage. Description implies it's the invitee's email but does not explicitly clarify parameter semantics beyond the schema. Minimal added value.
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?
Clearly states the action (invite), target (co-parent/partner/grandparent), mechanism (one-time invite link by email), and outcome (join household, see all kids + saves). Distinct from sibling tool 'parent_accept_household_invite'.
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?
Implies usage (when adding a co-parent) but no explicit guidance on when to use versus alternatives like 'parent_accept_household_invite' or 'parent_leave_household'. Missing exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are clearly grouped by prefix (admin_, daycare_, org_, parent_) and within each group have distinct, non-overlapping purposes. For example, parent_add_kid vs parent_remove_kid are unambiguous.
All tools follow a consistent snake_case pattern with role prefix and action_noun structure. Minor exceptions like 'nearby_programs' are standalone and do not disrupt the overall consistency.
With 72 tools, this is far beyond the typical well-scoped range of 3-15. While the tools cover multiple user roles, the count is excessive and likely overwhelming for an agent, falling into the 'too many' category.
The tool set covers most core workflows for parents, orgs, and admins, but notable gaps exist: there is no tool to create a program or daycare, and admin tools for approving pending claims or discoveries are missing, leaving dead ends.
