Reconnect an existing org without rotating keys (step 1 of 2): emails a 6-digit code to the owner. Then account_signin_verify. Prefer this over Recover.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=false, openWorldHint=true) already signal side effects; the description adds that an email is sent with a code, which is consistent. It does not mention code expiry or resend limits, but with annotations covering the safety profile, this is acceptable.
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 with zero waste: purpose, step, and alternative are all covered. The most critical information (what it does) is front-loaded.
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 one-parameter tool with an output schema, this description covers the purpose, the two-step flow, and the preferred alternative. Nothing essential is missing for an agent to invoke 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 description coverage is 0%, so the description must add meaning. It clarifies that the email parameter is the owner's email for an existing org, which is essential context the schema alone does not provide.
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 names a specific action: 'Reconnect an existing org without rotating keys' and clarifies it is step 1 of 2, sending a 6-digit code. It also distinguishes itself from the 'Recover' alternative, making its role unmistakable.
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 says 'Prefer this over Recover' and directs to account_signin_verify as the next step, giving a clear preference and flow. This is as direct as the calibration example and tells the agent when to choose this tool.
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.
The account tools are distinct flow steps (start/verify for signup, signin, recover) plus a status check and key usage, so they're largely unambiguous. However, the two start/verify pairs could be confused, and feedback_submit/zensched_guide are unrelated to account management, though their purposes are clear from descriptions.
The majority follow an 'account_' prefix with verb_style suffixes (e.g., account_signin_start). feedback_submit and zensched_guide break the pattern, but they are distinct actions and the naming is still readable and predictable overall.
11 tools is a reasonable number for an authentication-focused server, but the server is supposed to be for scheduling. With 8 of 11 tools being account/auth, the count feels heavy on setup and light on actual domain operations.
The tool surface is almost entirely authentication and account management, with no tools for scheduling core resources like locations, workers, shifts, or timesheets—despite the guide mentioning these as the intended workflow. The server would be useless for actual scheduling tasks.