Skip to main content
Glama
Mipiti MCP Server
by Mipiti

Release Behavioural Element

release_behavioural_element

Release an element held as written so the next extraction re-reads it from the description and standing answers, creating a model version.

Instructions

Release an element held as written (its rank is declared), so the next extraction reads it again from the description and the answers that stand. Mutating; creates a model version.

An element is held as written when a person or an accepted edit wrote it, or an earlier structured answer fixed it in place. No extraction changes it, so a correcting answer never reaches it; a question of closure held asks for this or an edit. Release it where the answers that stand should decide it; edit it instead where it holds something an accepted assumption or a person wrote that no answer states. Refused 409 not_declared for an element not held, created_whole for one an answer created with nothing in the text to read it from, and while a build holds the model.

A release is a judgment: a program's is refused with 403 and an escalation_id and parked for a person unless the workspace delegates behavioural_model_answered. Do not retry: report the escalation_id.

Returns what the release did, as edit_behavioural_element does.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "server_version": "<server_version>",
      "model_id": "<model_id>",
      "collection": "<collection>",
      "element_id": "<element_id>"
    },
    "name": "release_behavioural_element"
  }
}

Input Schema

NameRequiredDescriptionDefault
evidenceNo
model_idYesID of the threat model.
collectionYesThe collection of ``get_behavioural_model``'s ``ir`` the element belongs to.
element_idYesThe element's ``id``.
server_versionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.108.0

TDQS

A4.5/5.0
Behavior5/5

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

No annotations exist, and the description carries the full load: it declares the mutation, the side effect (creates a model version), and the exact failure surface — 409 `not_declared`, 409 `created_whole`, refusal while a build holds the model, and 403 with an `escalation_id` for programmatic callers unless the workspace delegates `behavioural_model_answered`, with an explicit do-not-retry instruction.

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?

Front-loaded with the action and its effect, and every paragraph carries operational content (decision rule, refusals, escalation). The stylized phrasing ('the answers that stand', 'held as written') and long parenthetical sentences cost some immediate parseability, but there is no filler.

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 no expansion beyond the pointer to edit_behavioural_element. Mutation semantics, refusal codes, escalation behavior, and the edit-vs-release choice are all covered; the only real gap is the unexplained `evidence` and `server_version` inputs.

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 60% and the description adds no meaning for the two undocumented parameters, `server_version` and `evidence` (including what evidence a release should carry). It does clarify the domain concept of `rank`=declared that the element_id/collection refer into, but that is contextual rather than parameter-level guidance. Baseline 3 is appropriate where the schema documents most fields.

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?

Names a specific verb (release) and resource (a behavioural element held as written, rank=declared), and states the effect: the next extraction reads it again from the description and standing answers. It explicitly distinguishes itself from the closest sibling, edit_behavioural_element, by the state of what the element holds.

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?

Gives a direct decision rule: release where the answers that stand should decide it; edit instead where the element holds something an accepted assumption or a person wrote that no answer states. It also names the trigger context (a closure question answered `held`) and the refusal cases that mean do-not-call.

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