Find a time a group can meet: no-login availability poll that picks the best meeting slot.
Scored across 2 tools
The two tools have completely distinct purposes: create_event sets up a new scheduling poll, while get_results reads responses from an existing poll. There is no ambiguity or overlap between them.
Both tool names follow the same verb_noun snake_case pattern: create_event and get_results. This is consistent and predictable.
Two tools feels thin for a server, though the narrow workflow of creating an event and then polling for results is cohesive. Each tool earns its place, but the surface is minimal.
The create-and-poll workflow is complete for the basic group scheduling use case, but there are no update or delete capabilities for events. Agents can work around mistakes by creating new events, so the gap is minor.
Create a free group-scheduling event (like When2meet/Doodle) and get a shareable link. Use this when a human asks you to find a time for a group to meet. Returns a public event_url anyone can open (no login) to mark when they're free, plus an admin note. Then poll get_results to see the best time.
| Name | Required | Description | Default |
|---|---|---|---|
| tz | No | Timezone label shown to participants, e.g. "US/Eastern" (default "local"). | |
| dates | Yes | Candidate dates to consider, each as YYYY-MM-DD. 1–31 dates. | |
| title | Yes | What the meeting is for, e.g. "Team sync" or "Dinner with friends". | |
| end_hour | No | Latest hour to consider, 1–24 (default 17 = 5 PM). | |
| start_hour | No | Earliest hour to consider, 0–23 (default 9 = 9 AM). | |
| slot_minutes | No | Time-slot granularity: 30 or 60 (default 60). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It discloses that the event is public, that anyone can open the returned event_url without login, and that an admin note plus the event URL are returned. It doesn't cover lifecycle, permissions, or rate limits, but the key behavioral traits are meaningfully surfaced.
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 dense sentences cover purpose, usage trigger, return values, and the follow-up action. There is no fluff or repetition of schema details, and the most decision-relevant information 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?
With no output schema, the description reasonably compensates by naming the event_url, the admin note, and the get_results polling step. The main gap is that the 'admin note' is left vague and lifecycle details are absent, but the agent has enough to invoke the tool and continue the workflow 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 100%, so the input schema already documents all six parameters. The tool description adds no per-parameter semantics beyond what the schema provides, so it meets the baseline but doesn't go above it.
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 opens with a specific verb and resource ('Create a free group-scheduling event'), adds a helpful analogy (When2meet/Doodle), and names the concrete deliverable (a shareable link). It clearly distinguishes the create action from the sibling get_results by framing get_results as the follow-up poll step.
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 explicitly states when to use the tool: 'Use this when a human asks you to find a time for a group to meet.' It also tells the agent the next step ('Then poll get_results to see the best time'), which clarifies workflow. It lacks an explicit when-not-to-use condition, so it doesn't fully earn a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current responses for a Whenly event and get the best meeting times (the slots where the most people are free). Pass the event slug (the code after /e/ in the event_url).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The 7-char event code from the event_url (the part after /e/). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry behavioral weight. It discloses that the operation is read-based and that it computes best times, but it does not describe output format, error cases, or explicitly confirm no side effects beyond the word 'Read'.
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 concise sentences with no filler. The first sentence front-loads purpose and outcome, and the second provides the exact parameter guidance needed.
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 simple one-parameter read tool with no output schema, the description covers what it does and how to construct the call. It stops short of describing the response shape, but the core usage context is adequately complete.
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 coverage is 100%, so the param is already well-documented. The description restates that the slug is the part after /e/ in the event_url, matching the schema exactly without adding new semantics.
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 reads responses for a Whenly event and derives best meeting times. It names a specific verb and resource, and the contrast with the sibling create_event makes the distinction obvious.
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 makes the use case clear: pass an event slug to read responses and get best times. It does not explicitly state when not to use this tool, but the single sibling create_event implies the read-vs-create split without needing an explicit exclusion.
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.
create_eventget_resultsFree no-login group availability poll; reads back the best meeting time for a group.
Free no-signup group scheduling (a modern When2meet): share one link, find a time for everyone.
Free no-signup group scheduling; share a link and rank times by who's free.
Agent-first meeting schedule polls for humans and agents. Create polls, vote, find times.
Add one secure layer between your agents and this server.
