Skip to main content
Glama
agentisend

agentisend

Lower key limits

set_limit
DestructiveIdempotent

Lower an API key's period budget or per-minute send ceiling to cap a job before it runs or stand the key down after a mistake.

Instructions

Purpose: lower the period budget or the per-minute ceiling on a key of this account — cap a job before it runs, or stand a key down after a mistake. NOT for: raising either one. A value above what the key has now is refused with human_action_required: that is the account owner's decision, made in the console. An agent_budget_exceeded or rate_ceiling_exceeded refusal is not cured here — wait for the period, or ask a person. Returns: the key id and confirmation the new, lower limits are stored.

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": {
      "api_key_id": "<api_key_id>",
      "budget_per_period": "<budget_per_period>"
    },
    "name": "set_limit"
  }
}

Input Schema

NameRequiredDescriptionDefault
api_key_idYesThe key whose limits to lower.
idempotency_keyNoYour own key for this action. Retrying with the same key returns the first result instead of doing it twice — send one whenever a retry could double the effect.
budget_per_periodYesMessages allowed per period. Must be at or below the key’s current budget; a key with no budget set can take any number, since every number is tighter than none.
rate_ceiling_per_minuteNoMax sends per minute. Must be at or below the key’s current ceiling.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
updatedNo
api_key_idNoIdentifier.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare destructive=true and idempotent=true, but the description adds meaning beyond them: raises are refused with human_action_required (an owner-console decision), and agent_budget_exceeded / rate_ceiling_exceeded refusals are not fixed here. This is exactly the kind of refusal/permission context an agent needs before calling.

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 labeled sentences (Purpose / NOT for / Returns) with zero filler, and the scoping constraint and exclusions are front-loaded. Every clause carries operational weight.

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?

Despite the mutation's destructive, refusal-bearing behavior, the description covers what it changes, what it refuses and why, and the confirmation returned. With annotations and an output schema present, nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the description adds cross-parameter meaning the schema does not: the operation lowers one of budget or ceiling, a value above the current one is refused, and a key with no budget accepts any value. That interplay goes beyond the per-field schema text.

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?

The description opens with a specific verb (lower) and resource (period budget or per-minute ceiling on a key), and immediately contrasts it with the sibling action it is not ('raising either one'). An agent can distinguish this from other key-management tools 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?

It gives explicit when-to-use cases ('cap a job before it runs, or stand a key down after a mistake'), an explicit when-not ('NOT for: raising either one'), and clarifies that a budget/ceiling refusal is not cured by this call. Nothing about selection is left to inference.

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