sqlguard_clientClassifies an agent wallet as a prior Exact-paying client (excluding operator wallets), returns lifetime USD, sku counts, and next ladder step.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | Agent or wallet id to classify |
| Name | Required | Description | Default |
|---|---|---|---|
| next | No | ||
| client | No | ||
| skus_bought | No | ||
| lifetime_usd | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description's safety burden is lower. The description adds behavioral context beyond annotations by revealing that operator wallets are filtered out and that the tool returns a classification plus specific metrics (lifetime USD, sku counts, next ladder step).
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?
One dense sentence packs the core purpose, an exclusion rule, and the key return fields without wasted words. The most important information is front-loaded.
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 single-parameter, read-only, idempotent tool with an output schema, the description is nearly complete: it gives the classification goal, the exclusion, and return components. Minor ambiguity remains around domain terms like 'ladder step', but the output schema likely covers the exact shape.
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 description coverage is 100%, with agent_id already explained as 'Agent or wallet id to classify'. The description largely repeats this concept ('agent wallet') and adds no additional parameter syntax, format, or edge-case guidance.
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 uses a specific verb ('Classifies'), names the exact resource ('agent wallet'), and states the definitive outcome ('prior Exact-paying client'), while also adding the operator-wallet exclusion. It clearly differentiates the tool from the generic sqlguard_* sibling list.
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 implies usage for classifying client status and retrieving lifetime USD/sku counts, but it does not explicitly say when to choose this tool over siblings like sqlguard_balance, sqlguard_profit, or sqlguard_denials. The 'excluding operator wallets' note provides a scope exclusion, not an alternative-tool routing.
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.
Multiple tools occupy the same job: challenge and pilot both sell the $100/7-day PASS; buy/catalog/cert/session/workday/validate are all legacy prepaid paths; handshake/protocol/require/sdk all provide onboarding/compliance guidance. Descriptions add PRIMARY/LEGACY labels, but an agent still has to parse heavy cross-references to avoid picking the wrong payment or authorization tool.
All tool names share the consistent sqlguard_ prefix and lower_snake_case style, and each name maps to a recognizable concept. However, the set mixes noun labels (denials, gravity, session) with verb labels (bind, buy, verify), so it is not a strict verb_noun API convention.
24 tools sits at the top of the 'heavy but borderline' range. Many could be collapsed because the legacy prepaid paths (session, workday, cert, buy, catalog, validate) are explicitly marked OFF TABLE for the primary wealth path, leaving redundant surface area.
The core lifecycle is well covered: handshake/onboarding, challenge/pilot unlock, bind/gate/verify pre-execution checks, denials inventory, effects verification, and client status. Minor gaps exist only around explicit invoice/refund/revocation tooling, but those appear to be handled externally or by expiry.