hai_intake

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

With no annotations, the description carries the full burden and answers the key behavioral questions: the write is immutable, the only return value is an intake id, and there are no side effects such as starting an agent. This goes well beyond what the raw schema alone conveys.

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?

Two sentences with no filler, and the core behavior and boundaries are front-loaded. Every clause adds information: immutability, return shape, and non-actionability.

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 one-parameter intake tool with an output schema and no annotations, the description covers purpose, behavior, return shape, and side-effect boundaries. It could be slightly stronger by naming sibling alternatives, but nothing essential is missing.

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%, so the description must add meaning for the sole parameter. 'Capture a raw thought' clearly maps the required 'raw' field to the thought content, which is sufficient for a single string argument. It omits length or format constraints, but those are not essential for this simple intake.

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 identifies a specific action ('capture'), a specific object ('a raw thought'), and a defining property ('immutably'). It also explicitly disclaims actionability and agent startup, which distinguishes it from sibling tools like hai_propose_next_step or hai_mission_start.

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 clearly implies the use case: persist an unprocessed thought for later without triggering action. It includes when-not-to-use guidance ('never actionable, never starts an agent'), but it does not name alternative tools or state explicit conditions for choosing among siblings.

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