aua_batch

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

Annotations already flag mutation (readOnlyHint=false), open-world behavior and non-idempotence; the description goes well beyond that by disclosing pre-execution validation, the exact stop conditions (error, wait timeout, Enter submission, 25s budget), and resume/skip semantics. The main remaining gap is what the result contains (presumably a stopped_at marker), which is not stated.

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?

Four short sentences, each carrying distinct information: capability, validation guarantee, stop conditions, and resume rule. Nothing is repeated from the schema or annotations, and the most load-bearing constraints (validation, stop, resume) are front-loaded.

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 single-parameter batching tool with open-world, non-idempotent semantics, the description covers validation, failure behavior, budget limits, and recovery. It is slightly incomplete in not describing the return payload or whether state must be primed first (e.g. via aua_ready), but no output schema exists to cover that.

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 single 'steps' parameter is only structurally constrained (minItems 1, maxItems 20, op enum, free-form args). The description partially compensates by capping the batch at 20 and telling the agent to use 'each operation's normal args', pointing args semantics back to the per-operation sibling tools, but it does not explain arg contents or ordering/dependency rules.

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 names a specific verb and resource ('Execute up to 20 known steps') plus scope (batch of known ops, each using its normal args). It implicitly separates itself from the single-action siblings by stressing 'known steps' and 'entire plan is validated before actions', though it never names a sibling explicitly.

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?

Usage is implied through 'known steps' (use when the plan is already determined, not when discovery is needed) and 'Resume from stopped_at; never replay completed/uncertain steps', which gives a recovery path. However, no alternative tool is named for discovery (e.g. aua_find) and there is no explicit when-not guidance, so the agent must infer the boundary with siblings.

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