Gate Check

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

With readOnlyHint=true already indicating safety, the description adds useful behavioral detail: it returns a decision of 'block' or 'allow', and on block the agent should surface the reason. It also clarifies that the tool evaluates the proposed call rather than executing it, which prevents misuse. No contradictions 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?

The description is two sentences, front-loaded with the primary purpose and immediate output semantics. It gives actionable usage guidance without redundancy or vague filler.

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 simple read-only policy check with two parameters and no output schema, the description adequately covers what the tool returns, when to use it, and its non-executing nature. It could optionally mention whether the policy is configurable, but given the schema and annotations, the description is sufficiently complete for agent invocation.

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 detailed examples for both tool_name and tool_input (e.g., {'command': 'rm -rf /'}). The description reinforces these examples in prose but does not add new parameter-level semantics beyond what the schema already provides. Baseline 3 is appropriate.

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 states a specific action ('evaluate a proposed tool call against ThumbGate policy BEFORE executing it') and explicitly defines the two possible outputs ('block' with reason, or 'allow'). This clearly distinguishes it from sibling tools that approve, track, or enforce actions rather than pre-check them.

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 provides concrete when-to-use guidance: 'when about to run a shell command, write/edit a file, or take any irreversible action.' It does not explicitly name alternatives or exclusions, but the timing (BEFORE executing) and action categories are clear enough for an agent to select this tool appropriately.

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