swarm.revenueGet swarm portfolio revenue intelligence: spend, revenue, LTV:CAC, margins, per-source scores. Call after swarm.research or swarm.settle to inspect realized economics.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No | Optional agent identity for quota accounting. |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, and destructiveHint=false, so no safety warning is necessary. The description contributes an important workflow behavior beyond the annotations: it exposes that this passes the fact that the data reflects realized economics only after the antecedent reports. There is no contradiction with the annotations.
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?
The prose is two sentences, front-loaded with outcome and output. It packs the most important information with no waste, while still explaining the scheduling relationship.
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?
With a single optional parameter, complete schema, and output schema available, the description adds the missing contextual pieces: the domain (economy, revenue), the key metrics, and the required call order. Nothing necessary for invoking this tool is absent.
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 has 100% parameter description coverage, defining the sole optional agent_id as an identity for quota accounting. The natural-language description does not expand on the parameter, so the baseline of 3 applies rather than a higher score.
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?
Description opens with a clear verb, 'Get swarm portfolio revenue intelligence', and lists concrete deliverables: spend, revenue, LTV:CAC, margins, per-source scores. That specificity distinguishes the purpose from sibling tools like swarm.research and swarm.settle, which are tied to data-generation rather than post-hoc economics.
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?
Includes explicit usage sequencing: 'Call after swarm.research or swarm.settle to inspect realized economics.' This provides when to call and why, which is strong guidance. It does not spell out exclusions or alternative-use cases, but the call ordering gives an agent a clear trigger.
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 namespaces help, but there is real overlap in purpose: city.check with x402.pay_and_fetch, city.sample with x402.probe, and multiple tools that verify a payment and then activate, credit, or settle something. The descriptions clarify which resource is being paid for, but tool names alone leave room for misselection.
Nearly every tool uses a lower-case dotted namespace.action pattern, making the set easy to scan. Some command parts are inconsistent, though: x402.networks, pulse.base, and commerce.credits_requirements read as nouns rather than actions, so the style is mostly but not fully uniform.
Nineteen tools is in the heavy range, and they span many subsystems: x402, city, commerce/quotas, swarm, ops, and Base network metrics. The number is not extreme, but the server feels like multiple product surfaces bundled under one MCP rather than a tightly scoped toolset.
The x402 lifecycle is well covered: discover, probe, pay, fetch, verify, sell, and settle, plus supportive commerce and city workflows. Notable gaps are refunds/quota-balance checks, seller resource update/removal, and invoice-like management for Stripe/card purchases, but none blocks the object workflows.