AtlaSent — Evaluate Many (batch)

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), description adds that results are returned in input order, batch_id provides idempotency, and closed-by-default errors are tagged with feature_not_enabled. This gives useful behavioral context.

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?

Three sentences, no wasted words. Purpose is front-loaded, then returns order, idempotency, and error behavior are efficiently stated.

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?

No output schema exists, so description should ideally explain return format. It says 'returns decisions in input order' but lacks details on decision structure, batch status, or potential errors. Adequate for basic understanding but incomplete for complex use.

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 coverage is 100%, but description adds value by clarifying the items array returns decisions in input order and batch_id provides idempotency, which is not evident from the schema alone.

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?

Clearly states it evaluates up to 100 actions against AtlaSent policies, returning decisions in input order. The verb 'evaluate' and resource 'many actions' are specific, and it implicitly differentiates from siblings like atlasent_evaluate (singular) and atlasent_evaluate_stream (streaming).

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?

Implies batch usage by stating 'up to 100 actions' and 'single request', but does not explicitly say when to use this vs. atlasent_evaluate or atlasent_evaluate_stream. No when-not or alternatives given, leaving the agent to infer.

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