tandem_decision

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

With no annotations, the description carries the burden and discloses important behavior: prepare is read-only and never starts the consultation, approvals and irreversible effects remain with the user, identity/quotes are checked rather than semantic entailment, and expired questions are rejected. It does not cover permissions, rate limits, or action-specific mutation side effects, so it is not fully complete.

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 purpose is front-loaded, and the six sentences are dense but mostly relevant policy and sequencing information. Some sentences are compressed and pronoun-heavy, but the description is not bloated.

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?

An output schema exists, so return values need not be described, and the description adds useful behavioral context. However, for a six-action tool with a deeply nested request schema and no annotations or parameter descriptions, the definition remains incomplete on action-specific input construction.

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 0%, and the nested request object contains many fields such as target, task_id, policy_id, cursor, max_bytes, and identifiers. The description names actions and policy concepts but does not map those actions to required fields or explain most parameter meanings, so it does not compensate for the schema gap.

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 first sentence gives a specific verb-and-resource purpose: record and answer a pending clarification against a pinned brief. It also mentions related actions like policy and prepare, but it does not clearly differentiate the tool from siblings such as tandem_reply or explain the full list/read scope.

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 supplies meaningful usage constraints: policy is opt-in, prepare is read-only and does not start consultation, source-backed basis must be recorded before reply, and expired questions cannot be answered. It lacks explicit sibling alternatives, so it stops short of a 5.

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