Make group polls from a chat and check who's winning. Voters need no account.
Scored across 2 tools
create_poll and get_results are clearly distinct in purpose: one writes a new poll, the other reads standings. There is no plausible overlap or misselection risk.
Both tools follow a consistent verb_noun snake_case pattern (create_poll, get_results). No deviations.
Two tools is thin, though it matches a minimal create-and-read polling service. It works, but an agent cannot do much beyond that without an additional primitive.
The core lifecycle (create poll, read results) is present, but there is no way to close voting, list a user's polls, update options, or delete a poll. These gaps could force agents into dead ends on common follow-up requests.
Create a Pickly poll to help a group decide something together (where to eat, which date, what to watch) and get a link to share in the group chat. Nobody needs an account to vote.
| Name | Required | Description | Default |
|---|---|---|---|
| options | Yes | 2 to 20 options, all of the optionKind. | |
| question | Yes | What the group is deciding, e.g. "Where do we eat on Friday?" | |
| maxChoices | No | multi polls only: how many options each person may tick. Leave out for no limit. | |
| optionKind | No | What every option is: a named thing, a calendar date, a time of day, or a place. | text |
| description | No | Optional extra context shown under the question. | |
| votingStyle | No | How people vote. multi: tick every option that works (the default, good for most choices). ranked: put the options in order; an instant runoff picks the winner. score: 1 to 5 stars each. swipe: yes or no per option, one card at a time. availability: yes, if need be, or no per option; best for finding a date that suits everyone. | multi |
| closesInHours | No | When voting closes, in hours from now. Defaults to 24. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safety profile (not read-only, not destructive, closed world), so the bar is lower. The description still adds real behavioral context beyond them: the call produces a shareable link and voters need no account. It does not discuss auth requirements for creating, editability, or closure defaults beyond what the schema says.
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 front-loaded sentences with no filler; the key benefit (share link) and the audience fact (no account to vote) both earn their place. It is slightly short of ideal for a seven-parameter tool with five voting styles, but nothing is wasted.
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 full schema coverage, no output schema, and safety annotations present, the description covers the essentials and usefully states the primary return value (a share link). It leaves minor gaps around the creation-side auth/privacy expectations and what happens after creation, but an agent can call it correctly as-is.
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 schema already carries all parameter meaning, including votingStyle, optionKind, and the per-option shape. The description contributes nothing parameter-specific, which is the correct baseline-3 outcome when the schema does the heavy lifting.
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 gives a specific verb and resource ('Create a Pickly poll') plus the concrete outcome ('get a link to share in the group chat'), with example use cases (where to eat, which date, what to watch). It does not explicitly name or contrast with the sibling get_results, but the create-vs-retrieve verbs make the split 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?
It clearly frames when to reach for this tool: group decisions with multiple participants, and it implies the follow-on step of sharing a link. There are no exclusions or explicit alternatives named (e.g. what to do if a poll already exists), so it falls short of 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 standings of a Pickly poll: who's winning, by how much, and whether voting has closed.
| Name | Required | Description | Default |
|---|---|---|---|
| poll | Yes | The poll's link (https://usepickly.com/p/…) or its id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds real value beyond that by disclosing what the response conveys — who is winning, by how much, and whether voting has closed — which is important since no output schema exists.
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?
One sentence, front-loaded with the verb and resource, and the enrichment (winner, margin, closed status) follows immediately. Nothing redundant or padded.
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 read-only, single-parameter tool with full schema coverage and no output schema, the description gives enough: what it returns conceptually and that it is a read of live standings. It stops short of noting edge cases such as a poll with no votes or invalid link handling.
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 is a single parameter with 100% schema description coverage already stating it accepts a link or an id. The description adds no further semantics about the poll argument, so the baseline of 3 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?
Specific verb ('read') plus a specific resource ('current standings of a Pickly poll'), with the content of those standings spelled out: winner, margin, and closed status. An agent can distinguish this from the sibling create_poll purely on the description.
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?
'Read the current standings' implies the use case, but there is no explicit statement of when to use this tool, when not to, or what the alternative is when you want something other than standings (e.g. raw votes or poll config). Usage is inferable, not stated.
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_pollget_resultsOne-link team polls: create polls, vote, fetch results, and close polls.
Create one-tap polls, share them by link or QR code, and read the results from your AI assistant.
Create, update and analyze PollUnit polls, scheduling polls, surveys and contests.
Create a group date poll in one sentence; participants vote with no account.
Add one secure layer between your agents and this server.