Skip to main content
Glama

Fast.io

by io.fast.mcp

intent

Destructive

Agent Intents: announce what you are working on in a workspace so peers see a collision before it happens. allocate a slot when work starts (content-free, and GET-OR-CREATE — it can hand back a slot you already hold), fill it once you know what to say (fill is also the heartbeat; there is no renewal verb), browse every live intent (topics only), expand for full detail including message, release when done. Call action='describe' for the full reference. Destructive: release.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNofill only: one-line label, max 256 characters. No newlines or tabs. This is what browse shows.
actionYesOperation. Use 'describe' for full action reference.
cursorNobrowse only: opaque cursor from a previous response. Omit for the first page.
intentNoWhat KIND of work this is — closed vocabulary, server-validated. Optional on allocate and fill.
messageNofill only: long-form detail, max 8192 characters. Absent from browse rows — read it with expand.
node_idNoallocate only: scope the declaration to one node. Omit for a workspace-wide intent. Part of the slot key.
versionNofill only, REQUIRED: the version you last read for this slot. Compare-and-set — a stale or omitted version is refused with 409.
intent_idNoIntent ID from allocate, or from a browse/expand row. Pass it back EXACTLY as received — do not reformat it.
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). Required for every action except describe. Intents are workspace-only — there is no share variant.

TDQS

A4.4/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing important behavioral nuances: allocate is GET-OR-CREATE and can hand back an already-held slot, fill acts as a heartbeat, browse returns topics only, expand returns full details, and release is destructive. These details are not present in the annotations and materially affect how an agent should invoke the tool.

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 dense but every clause earns its place: purpose, lifecycle, heartbeat semantics, GET-OR-CREATE behavior, browse/expand distinction, describe pointer, and destructive warning. It front-loads the main purpose and communicates a complex multi-action tool in a compact, useful way.

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 10-parameter, six-action tool with no output schema, the description covers the central workflow and key behavioral caveats. It does not spell out return shapes for allocate or describe, but the schema covers parameters and the description directs to action='describe' for full reference. A small gap remains, so 4 is appropriate.

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 the schema already documents every parameter thoroughly. The description adds action-level semantics rather than parameter-level detail, which is appropriate, but it does not add much beyond the schema. Baseline 3 is correct.

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

Purpose4/5

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

The description clearly identifies the resource ('Agent Intents') and the core purpose: announcing workspace work so peers see collisions. It names all six actions and their roles, making the tool's function unmistakable. However, it does not explicitly contrast with any sibling tool, so it earns a 4 rather than a 5.

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

Usage Guidelines5/5

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

The description gives a precise lifecycle: allocate when work starts, fill once content is known, browse live intents, expand for detail, release when done. It also provides an explicit exclusion ('there is no renewal verb') and directs users to action='describe' for the full reference. This is strong, actionable guidance for when to use each action.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool covers a clearly distinct domain (auth, storage, shares, comments, events, AI, etc.), and overlapping concepts like share vs. fileshare are explicitly disambiguated with deprecation notes and cross-references. An agent can reliably select the correct tool for a task without ambiguity.

Naming Consistency3/5

Tool names are all lowercase single words, but they mix nouns (user, org, workspace) with verbs (download, find, upload) and include a hyphenated 'how-to'. There is no consistent verb_noun or noun-only pattern, though the names are still readable and memorable.

Tool Count4/5

19 tools is slightly above the typical 3-15 sweet spot, but the platform's breadth (auth, file management, sharing, collaboration, AI, metadata, and help) justifies this count. Each tool represents a substantial domain area, so none feel redundant.

Completeness5/5

The toolset provides full lifecycle coverage for the platform: authentication, user/org/workspace management, file storage/upload/download/search, sharing (both quickshare and durable file shares), comments, events, metadata pipelines, AI assistance, and product help. No obvious dead ends or missing operations are apparent.

Resources