hai_recover

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly labels the operation as 'read-only advice', which tells the agent it will not mutate state. It does not define what 'smallest' means or describe error behavior, but for a simple read-only tool this is a strong disclosure.

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 sentence with no filler. The verb and primary object are front-loaded, and the parenthetical 'read-only advice' adds essential safety context without bloating the definition.

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 read-only tool, the description covers the main action, source selection, and safety profile, and an output schema exists to define return values. Minor gaps remain around explicit null-to-latest behavior and the exact meaning of 'smallest', but these are not blocking.

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 compensate. The phrase 'latest or named checkpoint' maps naturally to the optional checkpoint_id parameter: omit it for latest, supply it for a named checkpoint. The mapping is not stated explicitly, but it is strongly implied.

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 uses a specific verb and resource: 'Return the smallest recovery next action' from 'latest or named checkpoint'. The 'recovery' qualifier and 'read-only advice' framing distinguish it clearly from sibling tools like hai_get_next_step or hai_propose_next_step.

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 the tool should be used when the agent needs recovery advice based on a checkpoint, and it clarifies the source as latest or named. However, it does not explicitly state when to use this tool versus alternatives, nor does it name any sibling tools.

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