Check an email sign-in: pending (owner has not clicked yet) -> approved (returns api_key ONCE + reconnect instructions). EXAMPLE reconnect for Claude Code: claude mcp remove yetty; claude mcp add --transport http yetty https://mcp.yetty.ai/ --header "Authorization: Bearer " -s user
| Name | Required | Description | Default |
|---|---|---|---|
| login_ref | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses key behaviors: the API key is returned only once, the status transitions from pending to approved, and it includes reconnect instructions. This goes beyond what a schema would show and the example is actionable.
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 mostly concise, opening with a clear purpose. The long reconnect example adds length but is directly useful and avoids fluff. The overall structure is logical, though the example could be trimmed without losing essential info.
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?
The description covers the return value (api_key ONCE) and the state flow, which is helpful given no output schema. However, it lacks explanation of the `login_ref` parameter and does not address error cases or what happens on repeated calls after the API key is consumed. This leaves some gaps for a simple tool.
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 describes a single `login_ref` parameter, but the description provides no explanation of what `login_ref` represents. With 0% schema description coverage, the description must compensate, but it does not even mention the parameter, leaving its meaning ambiguous.
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 clearly states the tool's purpose: checking the status of an email sign-in. It distinguishes from siblings like 'yetty_login' and 'yetty_status' by focusing on the sign-in state (pending/approved) and the specific return of an API key. The verb 'check' and resource 'email sign-in' are explicit.
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?
The description implies usage after a login attempt, explaining the pending-to-approved flow and providing a concrete reconnect example for Claude Code. However, it does not explicitly list when to use this vs. alternative status or login tools, nor does it state when not to use it (e.g., if login is not initiated).
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.
Most tools have distinct purposes: batch start/file/end are clearly separated, as are signup, login, and template pulling. However, yetty_claim_status and yetty_login_status both check statuses (of parked upload vs email login) and could be confused without careful reading, though their descriptions clearly differentiate them.
All tools share the 'yetty_' prefix and use snake_case, but the pattern varies: some are verb_noun (batch_start, batch_file, pull_template), others are noun (status, claim_status, authoring_guide). While readable and consistent in prefix, the lack of a uniform verb_noun structure is a minor deviation.
10 tools is well within the ideal 3-15 range. Each tool corresponds to a necessary step in the workflow (parking files, approving, authenticating, pulling templates, and checking status), with no redundant or superfluous additions.
The tool set covers the full lifecycle from parking a batch to owner approval and post-authentication access, plus template retrieval. The main gap is lack of explicit cancellation or resend-email tools, but the flow seems self-consistent and agents can likely work around minor omissions.
