Skip to main content
Glama

SQLGuard — permission before production writes

by io.sqlguard

Handshake — what do you need?

sqlguard_handshake
Read-onlyIdempotent

FIRST tool on connect. Asks: What do you need? Pass { need: "…" }. Org/migrate/mutate/production → sqlguard_challenge (POST /v1/challenge → Exact unlock /v1/challenge/unlock amount 100000000). Company invoice → /gateway $299+. Session/Cert OFF TABLE as primary. Call before sqlguard_catalog when unsure.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
needNoWhat you need in one sentence (e.g. 'authorize one INSERT', 'bind human Intent Mandate', 'burst of writes', 'prepaid credits', 'portable gate before execute')
agent_idNoOptional agent or wallet id for routing context

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
askNo
matchedNo
optionsNo

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive; description adds context about being the first tool and the routing outcomes, including specific endpoints for challenges, without contradicting annotations.

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

Conciseness5/5

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

Description is compact yet dense, with each clause providing actionable routing or usage information; no fluff.

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

Completeness5/5

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

Given it's a simple handshake tool with full schema and output schema, the description covers purpose, routing, exclusions, and proper ordering relative to other tools.

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

Parameters4/5

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

Schema covers both parameters fully (need with examples, agent_id for routing context). Description reinforces need as a one-sentence intent and adds the important insight that the need value determines routing, which is not in the schema.

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

Purpose5/5

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

States clearly it is the 'FIRST tool on connect' and 'Asks: What do you need?' establishing its role as an initial intake/routing tool. It distinguishes from siblings by its position and explicit routing directives.

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

Usage Guidelines5/5

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

Provides explicit when-to-use guidance: 'FIRST tool on connect', 'Call before sqlguard_catalog when unsure', and gives conditional routes for various needs (org/migrate/mutate/production → sqlguard_challenge, company invoice → /gateway). Also states what is off-table (Session/Cert).

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.9/5.0
Disambiguation2/5

The tool set is dominated by overlapping buy/unlock paths (challenge, pilot, buy, catalog, cert, session, workday, sprint, profit, handshake) that are poorly differentiated, with many marked as legacy or off-table. Only a few tools (bind, gate, verify, effects) have clearly distinct roles.

Naming Consistency2/5

All tools share the sqlguard_ prefix, but the second part is a mix of nouns, verbs, and vague branding (gravity, profit, sprint, handshake). There is no consistent verb_noun pattern, making it hard to predict a tool's purpose from its name.

Tool Count3/5

24 tools is heavy for a permission gateway, and many are redundant legacy or alternative buy paths. While the count is within the 16-25 borderline range, the core functionality could likely be served by 8-10 tools.

Completeness3/5

The core authorization flow (handshake → challenge/unlock → bind/gate → verify) is present, but the surface is muddied by legacy and alternative paths that create dead ends. Missing tools for managing denials or configuring policies leave some gaps, though the central lifecycle is covered.

Resources