Skip to main content
Glama

Fast.io

by io.fast.mcp
OverviewDiscussionsAdmin

Agent Intents

intent
Read-only

Agent Intents (read): workspace-scoped declarations of what agents are working on. browse lists every live intent (topics only); expand returns full records. Writes are on intent_manage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesOperation. Use 'describe' for full action reference.
cursorNobrowse only: opaque cursor from a previous response. Omit for the first page.
intent_idsNoexpand only: one or more intent IDs. Accepts an array, a JSON array string, or a comma-separated string. Max 250.
workspace_idNoWorkspace ID (19-digit numeric). Intents are workspace-only — there is no share variant.
describe_actionNoWith action='describe': return one action's params and notes instead of the action index.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "describe",
-  "allocate",
-  "browse",
-  "fill",
-  "expand",
-  "release"
-]New value: +[
+  "describe",
+  "browse",
+  "expand"
+]
    • addedInput schema / properties / describe_action
      Added value: +{
+  "description": "With action='describe': return one action's params and notes instead of the action index.",
+  "type": "string"
+}
    • removedInput schema / properties / intent
      Removed value: -{
-  "description": "What KIND of work this is — closed vocabulary, server-validated. Optional on allocate and fill.",
-  "enum": [
-    "edit",
-    "read",
-    "upload",
-    "move",
-    "delete",
-    "analyze",
-    "organize"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / intent_id
      Removed value: -{
-  "description": "Intent ID from allocate, or from a browse/expand row. Pass it back EXACTLY as received — do not reformat it.",
-  "minLength": 1,
-  "type": "string"
-}
    • removedInput schema / properties / message
      Removed value: -{
-  "description": "fill only: long-form detail, max 8192 characters. Absent from browse rows — read it with expand.",
-  "type": "string"
-}
    • removedInput schema / properties / node_id
      Removed value: -{
-  "description": "allocate only: scope the declaration to one node. Omit for a workspace-wide intent. Part of the slot key.",
-  "minLength": 1,
-  "type": "string"
-}
    • removedInput schema / properties / topic
      Removed value: -{
-  "description": "fill only: one-line label, max 256 characters. No newlines or tabs. This is what browse shows.",
-  "type": "string"
-}
    • removedInput schema / properties / version
      Removed value: -{
-  "description": "fill only, REQUIRED: the version you last read for this slot. Compare-and-set — a stale or omitted version is refused with 409.",
-  "maximum": 9007199254740991,
-  "minimum": 0,
-  "type": "integer"
-}
    • changedInput schema / properties / workspace_id / description
      Previous value: -"Workspace ID (19-digit numeric). Required for every action except describe. Intents are workspace-only — there is no share variant."New value: +"Workspace ID (19-digit numeric). Intents are workspace-only — there is no share variant."
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: intents are workspace-scoped with no share variant, browse returns topics only while expand returns full records. Pagination/return-shape detail is left to the schema.

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?

Three tight sentences: identity/scope first, mode distinction second, routing to the write sibling last. No filler, and the most decision-relevant facts are front-loaded.

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?

There is no output schema, and the description compensates by sketching what each action returns (topic summaries vs full records). Cursor pagination and the describe action are only implied, but the schema covers those parameters, so coverage is adequate.

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 every parameter is already documented in the schema (including browse-only cursor and expand-only intent_ids). The description reinforces the browse/expand parameter mapping but adds no syntax or format detail beyond it, matching the baseline 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?

States a specific verb+resource ('Agent Intents (read): workspace-scoped declarations of what agents are working on') and immediately distinguishes the two read modes, browse vs expand. It also names the sibling that owns writes, so an agent can separate this tool from intent_manage without opening either schema.

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

Usage Guidelines4/5

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

It clearly routes writes to `intent_manage` and explains the browse/expand split (list topics vs full records). It does not cover the third action, 'describe', or when to prefer this over other read tools, so the guidance is strong but not exhaustive.

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

All Fast.io 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