Lost API key (step 1 of 2): sends a verification code to the org owner email. Then call account_recover_verify. Prefer account_signin_start if you only need to reconnect — Recover revokes ALL keys.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds crucial behavior beyond annotations: this is step 1 of a two-step flow, a verification code is sent to the org owner email, the next tool is account_recover_verify, and the overall recovery path revokes all keys. This significantly informs agent expectations, especially since annotations only show readOnlyHint false and destructiveHint false.
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 sentences, each adding distinct value: what the tool does, what to call next, and when to use an alternative. The critical warning about revoking keys is placed at the end but clearly highlighted. No wasted words.
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 a single parameter, the step context, next-step guidance, alternative routing, and security warning, this description fully equips an agent to call the tool correctly. The output schema exists, so return-value details are not needed.
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?
The schema only says the email property is a string titled 'Email', with 0% description coverage. The description compensates by specifying that the email is the org owner email and that a verification code is sent there, giving real semantic meaning to the only parameter.
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 action (sends verification code to org owner email) and clearly links to the recovery flow as step 1 of 2. It differentiates itself from account_signin_start and names account_recover_verify as the next step, so an agent can distinguish it from siblings without opening schemas.
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 when to prefer account_signin_start instead — when only reconnecting is needed — and warns that Recover revokes ALL keys. This is strong routing guidance that prevents misuse.
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 flows are mostly distinguishable: create, signup, signin, recover, and use_key have distinct purposes, and the descriptions include helpful preference guidance. The start/verify pairs and the similar signup/signin names create minor ambiguity, but descriptions resolve it.
Most tools follow a snake_case account_<action> pattern with clear start/verify pairs, and feedback_submit fits the verb_noun style. The naming is slightly inconsistent because zensched_guide is a bare noun and account_auth_status is not structured like the other action-oriented tools.
Eleven tools is within a reasonable range, and the multiple account tools each correspond to a distinct authentication flow. The count is slightly heavy on account management relative to the apparent scheduling domain, but no tool feels redundant.
The guide explicitly mentions fund, locations, workers, shifts, and timesheets, but none of those scheduling operations are exposed as tools. The server is essentially an account-authentication and feedback surface, and it even references missing tools like account_get and account_set_contact, so it severely under-serves the stated ZenSched purpose.