Fast.io

Metadata Management

metadata_manage

Destructive

Fastio workspace metadata (write): fold one field name into another, workspace-wide; create, replace or delete saved filters. Destructive: fields-merge (irreversible; unconfirmed it is a preview), filter-delete. Reads are on metadata. action='describe' gives the full reference.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Saved filter name, 1-100 characters, unique per workspace.
`action`	Yes	Operation. Use 'describe' for full action reference.
`confirm`	No	fields-merge: 'true' performs the IRREVERSIBLE workspace-wide merge; omitted, the call is a preview that changes nothing.
`filter_id`	No	Saved filter ID (from filters-list).
`predicate`	No	Saved filter predicate: JSON array of up to 5 AND-ed {field,operator,value} clauses; [] matches all.
`projection`	No	Saved filter projection (JSON object or array, stored as sent); only {"sort":{field,dir}} is applied.
`description`	No	Saved filter description, max 255 characters.
`template_id`	No	RETIRED (metadata templates were removed): supplying it fails the request on every action. Narrow by field name (fields-list).
`source_field`	No	The field NAME that is FOLDED AWAY and stops existing. Names, not ids.
`target_field`	No	The field NAME that SURVIVES and absorbs the source's values.
`workspace_id`	No	Workspace opaque ID (19-digit numeric ID or custom name). Required for every action.
`describe_action`	No	With action='describe': return one action's params and notes instead of the action index.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 10, 2026

changedInput schema / properties / action / enum

Previous value: -[
-  "describe",
-  "fields-merge"
-]New value: +[
+  "describe",
+  "fields-merge",
+  "filter-create",
+  "filter-update",
+  "filter-delete"
+]

addedInput schema / properties / description

Added value: +{
+  "description": "Saved filter description, max 255 characters.",
+  "type": "string"
+}

addedInput schema / properties / filter_id

Added value: +{
+  "description": "Saved filter ID (from filters-list).",
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / name

Added value: +{
+  "description": "Saved filter name, 1-100 characters, unique per workspace.",
+  "type": "string"
+}

addedInput schema / properties / predicate

Added value: +{
+  "description": "Saved filter predicate: JSON array of up to 5 AND-ed {field,operator,value} clauses; [] matches all.",
+  "type": "string"
+}

addedInput schema / properties / projection

Added value: +{
+  "description": "Saved filter projection (JSON object or array, stored as sent); only {\"sort\":{field,dir}} is applied.",
+  "type": "string"
+}

AddedOct 3, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds which specific actions are destructive (fields-merge, filter-delete) and that fields-merge is workspace-wide and irreversible unless confirm is set. The 'unconfirmed it is a preview' phrasing is slightly murky about what remains unverified, which keeps this short of a 5.

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 clauses with zero filler, front-loading the write scope, then the destructive-action list, then the read alternative and the describe escape hatch. Every sentence earns its place.

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 12-parameter, no-output-schema tool with a retired `template_id`, the description covers the safety-critical surface (which actions destroy data, preview behavior) and the alternatives. It relies on the schema for field-level detail, which is reasonable, but does not mention result shape or how filter_id is obtained.

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 coverage is 100% and the schema already documents every parameter, including the preview semantics of `confirm`. The description's only parameter-level contribution is pointing at action='describe', so the baseline 3 for schema-carried semantics is appropriate.

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 and resource ('Fastio workspace metadata (write)') and enumerates the concrete operations: field folding, saved-filter create/replace/delete. It explicitly distinguishes itself from the read sibling ('Reads are on `metadata`'), so an agent can route 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?

Gives clear routing context: use this for writes, use `metadata` for reads, and use action='describe' to get the full action reference. It does not, however, say when to pick fields-merge versus filter-* operations or state prerequisites beyond workspace scoping.

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

All Fast.io tools Inspect

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

Need Help?