Record a charge against a meter and ENFORCE the cap. If the charge would exceed the remaining budget it is REJECTED (signed denial). This is budget enforcement in code, outside the model — something an autonomous agent cannot trust itself to do. Returns remaining + a signed line-item.
| Name | Required | Description | Default |
|---|---|---|---|
| memo | No | What this charge was for | |
| amount | Yes | Amount to charge in the meter's units | |
| meter_id | Yes | The meter_id from meter_open |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that charges are capped and rejected if exceeding budget, and returns a signed denial. Annotations provide readOnlyHint=false and destructiveHint=false, and the description adds important context: budget enforcement is coded outside the model, which is critical for an autonomous agent. No contradiction with 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?
Two sentences that efficiently convey purpose, behavior, and return value. Front-loaded with the primary action ('Record a charge against a meter and ENFORCE the cap'), no redundant words.
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?
Given the tool has no output schema, the description explains the return format (remaining + signed line-item). The core behavior (cap enforcement, rejection on excess) is fully covered. For a mutation tool with 3 parameters, this is complete and actionable for an AI agent.
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% with descriptions for all three parameters. The description reiterates 'meter_id from meter_open' which adds slight context beyond the schema, but does not significantly enhance parameter understanding. Baseline 3 is appropriate as schema does the heavy lifting.
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 explicitly states the tool records a charge against a meter and enforces a cap. It uses specific verbs ('record', 'enforce') and distinguishes from siblings like meter_open and meter_status by highlighting the budget enforcement aspect.
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 explains when to use the tool (to charge a meter with cap enforcement) and implicitly when not to (e.g., to check status use meter_status). It explicitly notes this is for budget enforcement that an agent cannot trust itself to do, providing clear context. It could explicitly name alternatives, but the sibling list makes it clear.
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.
With 94 tools spanning overlapping concepts (multiple readiness/audit/grade tools, many status checkers, deprecated aliases like trust_* vs observation_*), agents will frequently struggle to pick the right one. While each tool is individually distinct, the sheer volume and conceptual overlap (e.g., audit_mcp, readiness_report, verify_mcp_ready, lookup_readiness, recommend_mcp, subscribe_grade_changes) create high misselection risk.
Most tools use snake_case with underscores, but the pattern is inconsistent: some are verb-first (audit_mcp, verify_mcp_ready, claim_start, check_engagement) while others are noun-first (receipt_issue, meter_open, work_order_open, agent_invoice_status). Deprecated aliases like trust_compare vs observation_compare further break consistency, though the majority remain readable.
94 tools is far beyond any reasonable scope for a single server, even one with broad ambitions like 'observatory + town'. The calibration notes 50+ as extreme mismatch; this server far exceeds that. Many tools are highly specific (e.g., factory_resolve_dead_letter, visit_touch_status, start_here) and could be consolidated or split into separate servers.
The server covers a wide range of domains (auditing, claiming, receipts, meters, escrow, work orders, gold rush, town, analytics) and offers many CRUD-like operations, but several lifecycle gaps exist: no cancel/close for work orders (only open/accept/deliver/accept_delivery), escrow (only open/attest/status), or meters (only open/charge/status). Given the massive scope, important operations are missing, though core workflows are present.