Skip to main content
Glama

Apply proposed changes

apply_proposal
DestructiveIdempotent

AI Agents: Use only after the person saw a proposal of a propose_ tool and said yes; say first when something would be sent to people in their system. Writes exactly what the proposal showed, skips a record that changed since, and keeps an undo where the system allows it. A proposal that needs approval in CRM Connector is refused with its approve link. Not for a change nobody proposed (use a propose_ tool first).

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": {
      "proposal_id": "<proposal_id>"
    },
    "name": "apply_proposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
proposal_idYesThe proposal id a propose_ tool returned.

Output Schema

NameRequiredDescriptionDefault
noticeNo
statusYes
changesYes
proposalIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / proposal_id / description
      Previous value: -"The proposal id propose_changes returned."New value: +"The proposal id a propose_ tool returned."
  2. Changed1 schema field changed
    • changedInput schema / properties / proposal_id / description
      Previous value: -"The proposal id one of the proposing tools returned."New value: +"The proposal id propose_changes returned."
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, but the description adds behavior the annotations cannot express: it writes the proposal verbatim, skips records that changed since, preserves an undo where supported, and returns an approve link instead of acting when CRM Connector requires approval. Those are the exact surfacing/conflict/refusal semantics an agent needs before a destructive write.

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 audience and precondition, and every clause carries a distinct rule (consent, announcement, verbatim write, skip-on-change, undo, approval refusal, exclusion). It is dense and the long compound sentences make it slightly harder to scan, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, open-world write with an output schema already covering return values, the description supplies the human-consent gate, the conflict-skip behavior, the undo caveat and the approval-refusal path. Nothing an agent needs in order to call it safely is missing.

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 single parameter is fully documented as coming from a propose_ tool, so the schema carries the weight. The description's reference to 'a proposal of a propose_ tool' reinforces provenance but adds no format, validity or reuse detail beyond what is already structured.

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 ('Writes exactly what the proposal showed') on a specific resource (a proposal produced by a propose_ tool), and explicitly separates itself from the propose_* family ('Not for a change nobody proposed'). An agent can place this tool precisely 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 Guidelines5/5

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

Gives a hard precondition (a person saw the proposal and said yes), a sequencing rule against the propose_ tools, an announcement obligation when writes reach people in their system, and an explicit exclusion ('Not for a change nobody proposed'). Both the when-to-use and when-not-to-use cases are named.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources