Skip to main content
Glama
Sign In

Ankra

by ai.ankra
OverviewDiscussionsAdmin

Approve cost decision

approve_cost_decision

Approve a cost decision (the twin of ankra cost decisions approve). plan_hash is the plan_hash get_cost_decision or list_cost_decisions answered: you approve the plan you read, and an approval is refused if the plan changed since. Nothing runs yet: execute_cost_decision runs it, or the cost autopilot does once its run_after passes. Needs billing.manage, or the write permission on the decision's cluster; the ledger decides.

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": {
      "decision_id": "<decision_id>",
      "plan_hash": "<plan_hash>"
    },
    "name": "approve_cost_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoYour reason or note, recorded on the decision.
plan_hashYesThe plan_hash a read of this decision answered (64 lowercase hexadecimal digits).
decision_idYesThe id of a cost decision, as list_cost_decisions shows it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: optimistic-concurrency behavior (an approval is refused if the plan changed since the read), explicit permission requirements (billing.manage or write on the decision's cluster), and clear non-execution semantics. These are exactly the operational facts the readOnly/destructive hints do not convey.

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?

Front-loaded with the action and the crucial 'nothing runs yet' caveat, then the token provenance, then permissions. Some density ('the ledger decides', the CLI twin parenthetical) but no sentence is 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?

Covers preconditions, permissions, side-effect scope, and follow-on tools for a mutation with no output schema. The only gap is that it does not say what the call returns (e.g., the updated decision state), which matters slightly given there is no output schema.

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 100%, so baseline is 3; the description adds real meaning by explaining that plan_hash is a token obtained from a prior read and that approval binds to that specific plan version. The note parameter is left to the schema, which is fine.

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 ('Approve a cost decision') and immediately scopes it against the family of siblings by declaring 'Nothing runs yet: execute_cost_decision runs it'. The plan_hash explanation ('you approve the plan you read') further pins down exactly what the action does.

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?

Explicitly names where plan_hash comes from (get_cost_decision or list_cost_decisions) and explicitly names the alternative (execute_cost_decision) plus the autopilot path for when execution happens. It also states the refusal condition, so an agent knows when this call will not apply.

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

All Ankra toolsInspect
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