create_hitl

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

With no annotations, the description carries the full burden, and it delivers: it discloses the create side effect, the mandatory authorization follow-up, the Telegram chat_id discovery prerequisite, and the Proof account/API key restart requirement. It does not describe return values or duplicate/overwrite behavior, which keeps it from a 5.

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 compact and front-loaded with the core purpose, then splits into Agent usage and ACCESS sections. Each sentence provides distinct, actionable information with no filler.

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 create tool with three parameters, nested channel variants, no output schema, and no annotations, the description covers the prerequisites, call sequencing, and channel-specific setup. It would be slightly more complete if it mentioned the expected response/ID and explicitly routed existing-config changes to update_hitl, but the agent can still invoke it correctly.

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 100%, so the baseline is 3. The description adds value by mapping 'channels' to approval destinations, 'timeout_seconds' to the default timeout, and by explaining that Telegram requires a chat_id obtained via create_chat_id_discovery. That workflow-level hint goes beyond what the schema alone provides.

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 opens with 'Create a HITL config' and specifies it defines which messaging channels receive approval requests and the default timeout. It clearly distinguishes this from related workflow tools by stating it must be followed by request_hitl_authorization and that create_confirmation consumes it afterward.

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 explicitly tells the agent to call request_hitl_authorization after creation, before using create_confirmation, and to call create_chat_id_discovery first for Telegram channels. It also gives the PROOF_API_KEY prerequisite and notes that start_login does not open this tool. It does not explicitly tell the agent to use update_hitl for existing configs, which would be the natural 'when-not-to-use' complement.

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