tf_request_approval

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

No annotations are provided, so the description carries the full burden. It discloses the delivery channel (Slack/CLI), the refusal condition (blocking policy), and the return of an approvalId. It does not mention whether the call blocks, side effects, permission requirements, or what happens on failure beyond 'refuses'. While it gives some key behavior, it is not comprehensive for a mutation-like action with no annotation support.

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, readable sentence that efficiently covers the core action, channels, refusal, and return. It front-loads the primary purpose. No redundancy or filler. It is appropriately compact for the information it conveys.

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?

Given there is no output schema and no annotations, the description should provide sufficient context for an agent to call the tool correctly. It explains the overall flow (send for approval, get approvalId), but omits details like what happens if the plan is missing, whether the call is synchronous or asynchronous, error conditions beyond 'refuses', and the exact nature of the returned approvalId (format or type). For a tool that triggers a human approval process, these are important gaps.

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 50%; only overridePolicy has a description, while workspaceId lacks any. The tool description does not clarify workspaceId, nor does it explicitly explain overridePolicy's purpose beyond what the schema already states. The mention of 'Refuses if policy findings are blocking' indirectly relates to policy, but does not map to parameter semantics. The description adds little value over the schema and fails to compensate for the missing workspaceId documentation.

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 clear action ('Sends the current plan for human approval') with the specific resource being the current plan. It also adds useful detail about the two delivery channels (Slack or CLI) and the refusal condition. It does not explicitly distinguish itself from tf_check_approval_status, but the mention of returning an approvalId to poll implies the next step, so the purpose is unambiguous.

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 implies it should be used after a plan exists and after policy checks (since it refuses on blocking findings). However, it does not explicitly state when to use it versus tf_plan, tf_policy_check, or tf_apply. It mentions returning an approvalId to poll, hinting at tf_check_approval_status but without naming it. This is enough to orient an agent but lacks explicit exclusions or alternatives.

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