Review Batch

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: information_profiles are read-only, separate retrieved target/context/explanation, set semantic_review_required=True, do not auto-convert QA->Cloze, and are excluded from the receipt hash; a content_hash appears on PASS. These are non-obvious behavioral traits an agent could not infer from the schema. It loses a point because terms like 'receipt hash' and 'gate recorded' are asserted without explaining the side effects or failure modes.

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?

It is front-loaded with the core action, but the body is a single run-on sentence with nested parentheticals covering several unrelated concepts (profiles, hashing, gate recording, detail levels). Every clause carries information, but the lack of sentence breaks and the dense jargon make it harder to parse than necessary.

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?

An output schema exists, so return-value explanation is not required, but for a six-parameter tool with no schema descriptions the definition leaves gaps: phase's role, the format/expectations of the CSV inputs, and what 'registered batch_id' means operationally are never addressed. The behavioral clauses about profiles and receipts are valuable, but the parameter-level completeness is insufficient for correct invocation.

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 define all six parameters, but it only partially does. It gives the 'detail' enum values ('compact' default, or 'full') and a conditional meaning for deck_dir, yet qa_csv, cloze_csv, phase, and batch_id (beyond 'registered') receive no explanation, leaving the two required inputs and the phase parameter opaque.

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 a specific verb and scope ('One-shot batch review: runs every check over QA + Cloze CSVs') and enumerates the outputs (aggregated report, fix hints, information_profiles, receipt), so it is clearly distinct from a single-check tool. It stops short of explicitly naming sibling alternatives such as validate_batch or pipeline_gate_check, but the 'one-shot' framing and the gate analogy make the scope legible.

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?

There is conditional guidance for the gate behavior ('If deck_dir is given and batch_id is registered... recorded like pipeline_gate_check'), which implies when this tool acts as a gate. However, it never states when to choose this over validate_batch, batch_auto_fix, or pipeline_gate_check, nor any exclusions or prerequisites for the CSVs.

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