Skip to main content
Glama
Mipiti
by Mipiti

Declare Foundation

declare_foundation

Marks a model as a shared foundation and stores its advertised controls so other models can delegate shared services like auth or logging.

Instructions

Mark a model as a shared foundation that advertises providable controls.

Mutating: records this model as a foundation and stores its advertised controls; other models can then delegate to them (see attach_foundation). A foundation is a shared service (auth, logging, a shared datastore) whose controls other models can rely on.

Each entry in provides advertises one of THIS model's controls as providable: {"control_id": "CTRL-07", "capability_label": "Validates session tokens", "description": "..."}. A capability always advertises a control (a proven mechanism), never an objective.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
model_idYesID of the model to declare as a foundation.
providesYesList of advertised-control dicts. ``control_id`` is required per entry; ``capability_label`` and ``description`` describe what the control provides to consumers.
visibilityNoWho may delegate to this foundation. "workspace" (default) makes it discoverable to every model in the workspace; "explicit" limits it to models explicitly attached.workspace
server_versionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.66.0
    • changedInput schema / properties / provides / description
      Previous value: -"List of advertised-control dicts (control_id required)."New value: +"List of advertised-control dicts. ``control_id`` is required per entry; ``capability_label`` and ``description`` describe what the control provides to consumers."
    • changedInput schema / properties / visibility / description
      Previous value: -"\"workspace\" or \"explicit\"."New value: +"Who may delegate to this foundation. \"workspace\" (default) makes it discoverable to every model in the workspace; \"explicit\" limits it to models explicitly attached."
  2. Addedv0.62.2
  3. Removedv0.62.2
  4. First observedv0.57.0

TDQS

A4.1/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses that the tool is mutating ('records this model as a foundation and stores its advertised controls') and defines what a foundation is, but says nothing about permissions, reversibility, idempotency, or whether re-declaring overwrites existing controls.

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

Conciseness4/5

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

Purpose and mutation status are front-loaded, followed by supporting definition and the provides example. Every sentence is relevant, though the grammar and layering are slightly dense.

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?

An output schema exists so return values need not be described, and the description covers the mutation and the core provides semantics. For a mutating, no-annotation tool it is nearly complete, but missing any note on permissions, side effects on other models, or overwrite behavior.

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

Parameters4/5

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

Schema coverage is 75%, and the description adds real meaning beyond the schema: it gives the exact shape of a provides entry and a key semantic constraint ('a capability always advertises a control (a proven mechanism), never an objective') that is not expressed in the schema. It does not elaborate on visibility or server_version, so not a 5.

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 ('mark a model as a shared foundation that advertises providable controls') and clearly distinguishes this from the sibling attach_foundation, which is the consumer side of the relationship. An agent can tell what this tool does without opening the 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?

Explains the delegation workflow and points to attach_foundation as the counterpart, giving clear context for when this tool applies. It lacks an explicit when-not to use it or any prerequisite/ordering guidance, so it falls short of the 5 bar.

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

Deploy Server

Other Tools