SQLGuard — permission before production writes

Validate SQL (burn credit)

sqlguard_validate

Legacy prepaid burn path — OFF TABLE as wealth. For production authorize use sqlguard_challenge → Exact $100 unlock → sqlguard_verify. This tool burns prepaid credits only. Never execute FAIL or unverified certs.

Input Schema

TableJSON Schema

Name	Required	Description
`sql`	Yes	Proposed SQL mutation to authorize in the sandbox
`agent_id`	Yes	Agent or wallet id holding prepaid credits to debit
`schema_ddl`	Yes	Postgres DDL snapshot (CREATE TABLE…) the SQL will run against

Output Schema

TableJSON Schema

Name	Required	Description
`decision`	No	Sandbox authorize decision
`signature`	No	Ed25519 signature over the certificate
`certificate`	No	Unsigned Execution Certificate payload
`credits_remaining`	No	Agent balance after debit

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 7, 2026

changedInput schema / properties / schema_ddl / description

Previous value: -"Postgres DDL snapshot (CREATE TABLEâ€¦) the SQL will run against"New value: +"Postgres DDL snapshot (CREATE TABLE…) the SQL will run against"

First observedAug 7, 2026

TDQS

B3.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

It adds a critical side effect beyond the annotations: this tool 'burns prepaid credits only.' It also warns not to execute FAIL or unverified certs. The cryptic 'OFF TABLE as wealth' phrase weakens clarity, but the cost behavior is meaningfully disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, but the first clause 'OFF TABLE as wealth' is cryptic and does not earn its place. The routing guidance is front-loaded and useful, yet the jargon reduces overall clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a credit-burning validation tool, it covers cost behavior, production routing, and a safety warning. Still, it does not clarify what the tool returns or what 'validated' means, and the legacy-vs-production distinction is only lightly sketched.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are already documented in the input schema. The description adds no additional parameter-level detail, which matches the baseline for fully covered schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as a 'Legacy prepaid burn path' and contrasts it with the production flow (sqlguard_challenge → sqlguard_verify), so an agent can place it among siblings. However, it never explicitly says the tool validates SQL; the core purpose is left to inference from the title and parameter descriptions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly routes production use to sqlguard_challenge and sqlguard_verify, and positions this tool as the legacy prepaid path. It does not fully enumerate when prepaid is appropriate, but the exclusion is explicit and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SQLGuard — permission before production writes tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.