queue_decision

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

With no annotations, the description carries full burden. It discloses that writes go to the real decisions table (not knowledge graph) and that resolution is via resolve_decision. But it omits details on side effects, authorization needs, rate limits, or whether queuing is reversible.

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?

Three sentences, no filler, front-loaded with the core purpose. Each sentence adds essential information: purpose, distinction from previous pattern, and resolution pathway.

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?

Considering the tool has 10 parameters and no output schema, the description does not cover return behavior, confirmation, or error conditions. The proposed_subtasks parameter is complex but not explained in the description. However, the description does mention the key resolution mechanism.

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 coverage is 90%, so the input schema already provides adequate descriptions for most parameters. The tool description adds no additional parameter-level meaning beyond what is in the schema, achieving baseline 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?

Description clearly states the tool queues a decision for human review, distinguishes itself by writing to the real decisions table instead of the knowledge graph, and explicitly replaces the autopilot pattern using add_learning with a specific title prefix. It also mentions resolution via resolve_decision, providing a complete purpose.

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?

Description provides explicit guidance by contrasting with add_learning pattern and noting resolution via resolve_decision. However, it lacks explicit 'when to use vs. when not to use' statements and does not mention alternatives among sibling tools beyond add_learning.

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