marrow_workflow_gate

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

With no annotations, the description must carry full behavioral disclosure. It does explain that the tool returns an assessment (allow/warn/review_required/block) and includes prior lessons/playbooks, implying a non-mutating evaluation. However, it does not explicitly state whether the tool has side effects, requires permissions, or impacts the workflow beyond returning a decision. This is a moderate gap for a gate tool.

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 a single, information-dense sentence that fronts the core purpose (risk gate) and immediately enumerates target actions and return values. It achieves maximal clarity in minimal length, with no filler or redundancy.

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?

The description conveys the tool's overall role and output, which is enough for most selection and invocation decisions. It does not explain how to interpret the returned values (e.g., what to do on block), but that is not strictly necessary for initial use, especially since the schema covers parameter semantics. The lack of an output schema and annotations is partially mitigated by the description's clarity.

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?

The input schema has 100% coverage with meaningful descriptions for all five parameters, including the enum for riskTolerance and a warning about context metadata. The description adds no additional parameter-level semantics, so it matches the baseline of 3.

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 clearly identifies the tool as a pre-action risk gate for specific high-risk operations (deploys, publishes, merges, DB migrations, key rotation, destructive commands, production work). It lists concrete return values (allow, warn, review_required, block) and distinguishes it from sibling tools, which focus on memories, keys, handoffs, etc.

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 states when to use the tool: before actions in listed high-risk categories. It does not explicitly name alternatives or say when not to use it, but the list of covered operations provides solid contextual guidance. Given the sibling set contains no similar gate tool, the usage context is clear enough.

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