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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: one shared quota reservation and per-call independent outcomes, implying partial success is possible. It does not state what happens when some calls fail or how errors are surfaced per call, leaving that behavior partly opaque.

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?

Front-loaded with the core behavior, then the exclusion list, then a compact illustrative example. Every sentence carries information, though the example is somewhat verbose as a literal JSON literal in prose.

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 values need not be described, and annotations cover the safety profile. The description still omits how partial failures appear in results and how idempotency_key interacts with retries, which matter for a batch tool. It is adequate but not fully complete for a fan-out operation.

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?

The description's example does clarify the shape of a call object (operation plus arguments), which is useful. However, with only 50% schema coverage, the idempotency_key parameter is left entirely to the schema, and the description never explains operation selection beyond the example. The description adds less parameter meaning than the schema already provides.

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?

States a specific verb and resource – running up to ten independent read calls in parallel under one quota reservation – and distinguishes itself from the single-call siblings by that batching scope. An agent can immediately tell this is the fan-out read tool.

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?

Explicitly names two tools that cannot be batched (build_dossier and utilities), which gives concrete when-not guidance, and the ten-call cap implies single calls should use the individual siblings. It stops short of explicitly saying 'use a single tool when you have one call,' so it is strong but not fully exhaustive.

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