Request a payout of your confirmed referral credits. Payouts are not enabled yet — no transfer provider is configured, so this call reports that and moves no funds. When enabled it will require a registered payout address (set via PATCH /api/agents/me) and a confirmed balance of at least $10, and will withdraw the full balance.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | Your API key from register_agent. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description clearly discloses that no transfer provider is configured, so the call currently reports an unavailability condition and moves no funds. This goes well beyond the annotations, which only state readOnlyHint=false and destructiveHint=false, and gives an agent an accurate model of side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences deliver the core purpose, current limitation, and future requirements with no filler. The key distinction—'moves no funds'—is front-loaded and immediately actionable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with no output schema, the description supplies sufficient context: what the tool requests, why it currently cannot complete the request, and what conditions will govern it once enabled. An agent can decide whether and how to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully documents the only parameter, api_key, at 100% coverage. The description does not add parameter-specific detail beyond mentioning the payout address via PATCH /api/agents/me, which is not a parameter of this call. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Request a payout of your confirmed referral credits.' It also clearly distinguishes current behavior (reports that payouts are not enabled) from future behavior, so an agent understands precisely what the tool does and what it does not do.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: payouts are not enabled yet, so the tool is currently non-functional for actual transfers. It also specifies future requirements (registered payout address, confirmed balance of at least $10, full balance withdrawal), though it does not explicitly name sibling tools as alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The discovery-oriented tools—search_deals, compare_vendors, track_changes, and plan_stack—overlap in purpose and can be confused, especially for queries like 'What's cheaper than Vercel?' or 'Are free tiers being removed?'. The referral and account tools are clearly distinct, but the overlapping query surface lowers the overall disambiguation quality.
Most tools follow a consistent verb_noun pattern such as check_balance, submit_referral_code, and request_payout. Two tools deviate: 'leaderboard' is a bare noun and 'my_referral_codes' uses a possessive prefix, creating minor inconsistency.
Twelve tools is well within the ideal range and each tool covers a meaningful part of the AgentDeals domain: deal discovery, referral management, agent registration, payouts, and social routing. None of the tools feel redundant or extraneous.
The tool surface covers the main agent lifecycle well: registration, referral code submission and retrieval, balance checking, payouts, and friend management. Minor gaps exist—there is no way to update or remove a submitted referral code, and the payout address must be configured via an out-of-band API endpoint.
