Decide Proposals

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

With no annotations, the description carries the full burden and does so: it declares the tool mutating, states each item runs in its own transaction in the given order, and specifies that one refused item does not roll back the others and returns that item's escalation_id among the outcomes. Delegation-rule constraints and the batch limit are additional behavioral context an agent could not infer from the schema.

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 batch action and its cap are front-loaded and every sentence carries information. However, the clause about a refused program receiving its escalation_id beside the others' outcomes is densely phrased and slightly hard to parse on first read.

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 mutating batch tool, the description covers ordering, transaction isolation, partial failure, the size limit, and the delegation context. Return values need not be explained because an output schema exists.

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 83%, so the schema already documents most parameters, and the description adds little per-parameter detail. Its one meaningful contribution is framing each item as behaving exactly as decide_proposal does, which implicitly extends note, expires_at, and record_only semantics — but this is inference rather than stated meaning.

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?

States a specific verb (decide) applied to a specific resource (several proposals and escalations of one model), with a hard batch cap of 200 and per-item equivalence to decide_proposal. This cleanly separates it from the singular decide_proposal and from list_proposals without opening either schema.

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?

Explicitly prescribes when to use it: to clear a review queue's parked decisions in one call rather than one at a time, which names both the motivating scenario and the rejected alternative. The 200-item ceiling and the per-item-failure rule give the agent clear operating boundaries.

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