Get the aggregated payment graph for a multi-agent session. Returns total USD moved, transaction count, and a chronological list of all payments made during the session. Use for cost accounting, audit, or to show a human what an agent run spent.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session or task ID — the same ID used in receipt.create calls |
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?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description is not responsible for safety disclosure. It supplements by explaining the aggregated output and its chronological nature, adding behavioral context beyond annotations. No contradictions exist.
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 description is two sentences, starting with the primary action and result, then adding supporting output details and use cases. Every sentence contributes value with no redundancy or filler.
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?
No output schema exists, so the description appropriately explains what is returned (total USD moved, transaction count, chronological list). For a simple read-only tool with one parameter and strong annotations, this description fully covers purpose, output, and applicable contexts.
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?
Schema coverage is 100%; the only parameter 'session_id' is clearly described in the schema as 'Session or task ID — the same ID used in receipt.create calls'. The description does not add further parameter-level detail, which is acceptable given the schema's sufficiency, so 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 starts with a specific verb 'Get' and clearly defines the resource as 'the aggregated payment graph for a multi-agent session'. It enumerates exact outputs (total USD moved, transaction count, chronological list) and explicitly contrasts with use cases like cost accounting and audit, distinguishing it from siblings such as receipt.create and compute.cost.
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 explicit use cases: 'Use for cost accounting, audit, or to show a human what an agent run spent.' This gives strong contextual guidance, though it does not explicitly name alternative tools or state when not to use this tool, so a perfect score is not warranted.
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.
Many tools have overlapping purposes, such as multiple stablecoin routing options (route vs stability.stablecoin_route), several compliance pre-checks (flow_check, policy.check, mercury.ach_authorize), and numerous FX/stability tools (oracle.stability, stability.corridor, market.fx, fx.rate). Even with detailed descriptions, the boundaries are subtle and an agent could easily select the wrong tool.
The dot-separated namespace convention is mostly consistent and readable, but verb vs noun usage varies (e.g., settlement.execute vs batch_settle vs route). Subscription tools also mix forms (intelligence.subscribe vs intelligence.subscription.get/delete), showing minor inconsistency.
81 tools is an extreme count for a settlement server. Even accounting for the broad 'institutional' scope, the volume overwhelms the core purpose and creates a heavy cognitive load for agents, far beyond the typical 3-15 well-scoped tool set.
The core settlement lifecycle is well-covered (quote, execute, track, receipt, batch), but there are notable gaps such as missing policy update/delete and no receipt retrieval (only create). While many tangential domains are over-covered, certain CRUD operations are absent, creating dead ends.