Zero-auth MCP server for sending a reminder to anyone with a public UnRemind.me page. No account or token. The recipient approves it before it enters their list.
Scored across 2 tools
The two tools have clearly distinct purposes: one provides guidance about the submission process and the other performs the actual submission. There is no overlap or ambiguity in their roles.
Both tool names follow a consistent verb_object snake_case pattern: get_submission_guidance and submit_unreminder. The naming is predictable and readable.
With only two tools, the count is slightly under the typical 3-15 range, but it is justified for a narrowly scoped submit-only server. Each tool serves a distinct, necessary function.
The server covers its stated submit-only workflow well: guidance for whether/how to submit, and the submission action itself. A lookup or status tool might be a nice addition, but recipient approval and editing are explicitly handled outside this MCP, so there are no critical dead ends.
Explains what happens to a submitted Unreminder, what makes one likely to be accepted, sending limits, and what else UnRemind.me offers agents. Call this if you are unsure whether or how to submit.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already set readOnlyHint=true, and the description is consistent with a read-only explanatory tool. It adds useful behavioral context by stating what the explanation covers, including acceptance factors and limits, beyond what the empty schema and annotations reveal.
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 no filler: the first compactly lists the content areas, and the second gives an actionable call heuristic. The most important usage guidance is front-loaded and every sentence earns its place.
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 zero-parameter, read-only guidance tool, this description is complete: it explains what the tool provides, why an agent would call it, and the condition under which it should be used. No return value is promised, and no output schema exists, so nothing essential is missing.
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?
There are zero parameters and the schema fully covers that with an empty properties object, so there is no parameter ambiguity. The description adds no parameter information because none is needed; the baseline for zero-parameter tools applies.
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 uses a specific verb (Explains) and names the exact resource (a submitted Unreminder) and the topics covered: acceptance likelihood, sending limits, and additional offerings. It is clearly distinguished from the sibling submit_unreminder because it is the explanatory counterpart to actually submitting.
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 gives an explicit call condition: 'Call this if you are unsure whether or how to submit.' The when-not case and the alternative submit_unreminder are implied rather than named, so it stops just short of fully explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sends a reminder to someone who has a public UnRemind.me page, on behalf of the person you are helping. It does NOT appear in the recipient's list immediately: it lands in their 'Submitted to you' queue for them to approve, edit or decline. You need the recipient's username, which the person you are helping will have — it is the last part of their page URL, e.g. unremind.me/johndoe. Do not guess a username: there is deliberately no lookup, and a wrong guess sends someone else's reminder to a stranger.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | Detail the recipient needs to act on it: context, links, what done looks like. Optional but strongly preferred — a bare title often gets declined. | |
| title | Yes | Short and action-oriented, e.g. 'Send the signed lease back'. This is what the recipient sees first. | |
| due_at | No | ISO 8601 with a UTC offset, e.g. 2026-09-02T14:00:00-04:00. Only set this if a real deadline was stated; an invented one is worse than none. | |
| page_key | No | Only needed if the recipient has made their page private. It is part of the link they shared. Omit otherwise. | |
| username | Yes | The recipient's UnRemind.me username — the last part of their page URL, e.g. 'johndoe' for unremind.me/johndoe. | |
| via_channel | No | How you are reaching us, e.g. 'Claude Code'. Shown to the recipient as the CHANNEL the person used, never as the sender. Optional. | |
| submitter_name | No | The name of the PERSON you are sending on behalf of — not your own name as an agent. The recipient sees this. Required UNLESS they have set it in this server's configuration. | |
| submitter_email | No | The sending person's email — how they receive the status link and the recipient's answer, and what lets them raise their sending allowance by signing in. Required UNLESS they have set it in this server's configuration. Ask them for it; never invent one. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all false (no hints), so the description fully carries the burden. It discloses that the reminder lands in a 'Submitted to you' queue for approval rather than appearing immediately, explains that it is sent on behalf of the person and the recipient sees the submitter's name, and warns that there is no username lookup. These are important behavioral facts beyond what annotations provide.
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 well-structured and front-loaded with the core behavior and timeline. Each sentence contributes meaningful information: the queue behavior, the username source, and the explicit warnings. No redundant or filler sentences; it is appropriately detailed for an 8-parameter tool.
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 8 parameters and no output schema, the description covers the essential workflow, the on-behalf semantics, the queue mechanics, and all parameter pitfalls. It gives enough for an agent to safely call the tool without guessing usernames or inventing emails, which are the most likely errors. No critical gap remains.
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?
With 100% schema description coverage, the baseline is 3. The description adds substantial guidance beyond the schema: notes should be strongly preferred or risk declination, due_at should only be set if a real deadline exists, and submitter_email should never be invented and must be asked for. These add critical usage nuances that are not present in the schema.
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 states a clear verb ('Sends a reminder'), a specific resource (someone with a public UnRemind.me page), and the on-behalf relationship. It also distinguishes itself from the sibling get_submission_guidance by being about the actual submission action. The queue behavior is mentioned, making it unambiguous.
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 gives explicit context for when to use the tool: when the helper has the recipient's username from their page URL, and it strongly warns against guessing. It does not explicitly contrast with the sibling tool get_submission_guidance, but its purpose is clear. A brief note that get_submission_guidance is for crafting content would have pushed this to a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_submission_guidancesubmit_unreminder
Add one secure layer between your agents and this server.