Skip to main content
Glama

Elicitly Pro

by ai.elicitly
OverviewDiscussionsAdmin

Ask a human to choose options

elicit_selection

Ask a human to choose one or more options from a caller-supplied list (disambiguation, record matching, picking work items). Async like elicit_approval: returns a pending request decided on the hosted review page; the chosen option ids come back via elicit_result as selectedIds. Options render as rows of a table the Liquid templates and css can customize. Defaults to single-select — raise maxSelections for multi-select.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cssNoCustom CSS injected on the review page to style the option table.
labelsNoRelabel or localize the action buttons (submit, decline). Each label is trimmed, 1-40 characters; unknown keys are rejected. Button placement and styling stay fixed.
messageYesThe instruction shown above the option list — say what the reviewer is choosing and why.
optionsYesThe choices (1-500). Each option is an object with a required unique `id` (returned in `selectedIds`) plus any extra keys, which `rowTemplate` / `hoverTemplate` can reference (e.g. {{ option.name }}).
rowTemplateNoLiquidJS template producing the <td> cells of one option row; the option is exposed as `option` (e.g. <td>{{ option.name }}</td><td>{{ option.score }}</td>). Any link must carry target="_blank" — without it the click replaces the option table with the linked page and the reviewer loses the form. Default: a single cell of `option.label`, falling back to `option.id`.
hoverTemplateNoLiquidJS template for a per-option hover/details card; the option is exposed as `option`. Omit for no hover card.
maxSelectionsNoMost options the reviewer may pick (default 1 = single-select; clamped to the option count).
minSelectionsNoFewest options the reviewer must pick to submit (default 1; 0 allows none).
footerTemplateNoLiquidJS template producing the table footer rows (no variables). Omit for no footer.
headingTemplateNoLiquidJS template producing the <th> cells of the table header (no variables). Omit for no header row.
expiresInSecondsNoHow long the request stays decidable, in seconds (default 3600, clamped 60-604800 — 1 minute to 7 days).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusYesAlways `pending` at creation.
expiresAtYesWhen the request stops being decidable (timestamp).
reviewUrlYesURL of the hosted review page where a human decides this request.
elicitationIdYesUnique id of the created request — pass it to elicit_await / elicit_status / elicit_result / elicit_cancel.
elicitationDeliveredYesTrue when the request was also pushed to the connected client as a url-mode elicitation; when false, surface `reviewUrl` to the human yourself.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / rowTemplate / description
      Previous value: -"LiquidJS template producing the <td> cells of one option row; the option is exposed as `option` (e.g. <td>{{ option.name }}</td><td>{{ option.score }}</td>). Default: a single cell of `option.label`, falling back to `option.id`."New value: +"LiquidJS template producing the <td> cells of one option row; the option is exposed as `option` (e.g. <td>{{ option.name }}</td><td>{{ option.score }}</td>). Any link must carry target=\"_blank\" — without it the click replaces the option table with the linked page and the reviewer loses the form. Default: a single cell of `option.label`, falling back to `option.id`."
  2. Changed14 schema fields changed
    • addedInput schema / properties / css / description
      Added value: +"Custom CSS injected on the review page to style the option table."
    • addedInput schema / properties / expiresInSeconds / description
      Added value: +"How long the request stays decidable, in seconds (default 3600, clamped 60-604800 — 1 minute to 7 days)."
    • addedInput schema / properties / footerTemplate / description
      Added value: +"LiquidJS template producing the table footer rows (no variables). Omit for no footer."
    • addedInput schema / properties / headingTemplate / description
      Added value: +"LiquidJS template producing the <th> cells of the table header (no variables). Omit for no header row."
    • addedInput schema / properties / hoverTemplate / description
      Added value: +"LiquidJS template for a per-option hover/details card; the option is exposed as `option`. Omit for no hover card."
    • addedInput schema / properties / labels / description
      Added value: +"Relabel or localize the action buttons (submit, decline). Each label is trimmed, 1-40 characters; unknown keys are rejected. Button placement and styling stay fixed."
    • addedInput schema / properties / labels / properties / decline / description
      Added value: +"Replacement label for the decline button."
    • addedInput schema / properties / labels / properties / submit / description
      Added value: +"Replacement label for the submit button."
    • addedInput schema / properties / maxSelections / description
      Added value: +"Most options the reviewer may pick (default 1 = single-select; clamped to the option count)."
    • addedInput schema / properties / message / description
      Added value: +"The instruction shown above the option list — say what the reviewer is choosing and why."
    • addedInput schema / properties / minSelections / description
      Added value: +"Fewest options the reviewer must pick to submit (default 1; 0 allows none)."
    • addedInput schema / properties / options / description
      Added value: +"The choices (1-500). Each option is an object with a required unique `id` (returned in `selectedIds`) plus any extra keys, which `rowTemplate` / `hoverTemplate` can reference (e.g. {{ option.name }})."
    • addedInput schema / properties / rowTemplate / description
      Added value: +"LiquidJS template producing the <td> cells of one option row; the option is exposed as `option` (e.g. <td>{{ option.name }}</td><td>{{ option.score }}</td>). Default: a single cell of `option.label`, falling back to `option.id`."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "elicitationDelivered": {
+      "description": "True when the request was also pushed to the connected client as a url-mode elicitation; when false, surface `reviewUrl` to the human yourself.",
+      "type": "boolean"
+    },
+    "elicitationId": {
+      "description": "Unique id of the created request — pass it to elicit_await / elicit_status / elicit_result / elicit_cancel.",
+      "type": "string"
+    },
+    "expiresAt": {
+      "description": "When the request stops being decidable (timestamp).",
+      "type": "string"
+    },
+    "reviewUrl": {
+      "description": "URL of the hosted review page where a human decides this request.",
+      "type": "string"
+    },
+    "status": {
+      "const": "pending",
+      "description": "Always `pending` at creation.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "elicitationId",
+    "status",
+    "reviewUrl",
+    "expiresAt",
+    "elicitationDelivered"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behaviors beyond the annotations: it is asynchronous ('returns a pending request decided on the hosted review page'), results come via elicit_result as `selectedIds`, and it defaults to single-select with a note to raise `maxSelections` for multi-select. These details are not present in the annotations, which only state non-destructive and non-idempotent. The description adds meaningful behavioral context without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, front-loading the core purpose in the first sentence, then covering async behavior, result mechanism, customization, and default selection mode in subsequent sentences. Every sentence adds value without redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 11 parameters and nested objects, the description gives a solid high-level overview: it explains the async nature, result retrieval, customization options, and default behavior. The output schema is present, so return values are covered elsewhere. While it doesn't explicitly address when to use this tool over other elicit_* siblings, the use cases and purpose provide adequate context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all 11 parameters have descriptions in the schema. The tool description adds minimal parameter-specific meaning beyond the schema, such as clarifying the default of `maxSelections`. Since the schema already documents each parameter thoroughly, the description's contribution is marginal, aligning with the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Ask a human to choose one or more options from a caller-supplied list' and gives concrete use cases (disambiguation, record matching, picking work items). The verb 'choose' and the resource 'options' are specific, and the use cases help distinguish it from sibling tools like elicit_approval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool via the listed use cases, but it does not explicitly mention alternatives or when not to use it. The mention 'Async like elicit_approval' hints at similarity but stops short of contrasting selection with approval. It gives enough guidance for typical usage but lacks explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Elicitly Pro toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources