Skip to main content
Glama

SQLGuard — permission before production writes

Instant Cert — LEGACY taste (OFF TABLE as wealth)

sqlguard_cert
Read-onlyIdempotent

LEGACY taste only — OFF TABLE as wealth/primary. One Exact Instant Cert $0.05. Wealth path: sqlguard_challenge Exact unlock $100 OR Gateway invoice $299. Then sqlguard_verify before execute.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYesExact mutating SQL to authorize
agent_idYesAgent or wallet id for the certificate receipt
schema_ddlYesCREATE TABLE … schema snapshot

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
priceNo
paymentNo
productNo
endpointNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / schema_ddl / description
      Previous value: -"CREATE TABLE … schema snapshot"New value: +"CREATE TABLE … schema snapshot"
  2. First observed

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already carry readOnly/openWorld/idempotent/destructive context, so the bar is lower. The description adds that this is the legacy path, costs $0.05 per cert, and must be followed by sqlguard_verify, but it does not explain what happens when the cert is issued or what constraints apply. 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.

Conciseness2/5

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

The text is short, but the phrasing is cryptic and jargon-heavy ('LEGACY taste', 'OFF TABLE as wealth/primary', 'Exact Instant Cert'), and the workflow instruction is compressed into a long run-on sentence. A few clear sentences would be more useful.

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?

The schema descriptions plus annotations plus output schema cover a fair amount of context. However, the core meaning of 'cert' and what the agent is being asked to authorize is still unclear, and the description relies on cryptic status labels to convey when the tool is appropriate.

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?

Input schema covers all three parameters with meaningful descriptions, so the baseline is 3. The description does not add any additional meaning about the parameters themselves.

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

Purpose2/5

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

The description never states a concrete action; it refers to 'LEGACY taste' and 'One Exact Instant Cert $0.05' but does not say what the tool does with agent_id, schema_ddl, and sql. The title 'Instant Cert' is the clearest signal, which is too close to a tautology. It does differentiate 'legacy' from the challenge/Gateway path, but not by explaining the tool's function.

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 gives explicit routing: use this only for 'LEGACY taste', not for wealth/primary, and names sqlguard_challenge and Gateway invoice as the wealth alternatives. It also tells the agent to call sqlguard_verify before executing, which is a concrete workflow instruction.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.