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

Beyond the annotations (readOnlyHint false, destructiveHint true, idempotentHint false), the description adds critical behavioral detail: partial success is normal, the response must be inspected rather than assuming all rows succeeded, and writes land in a shared AIsa workspace with no per-caller isolation. This explains the practical consequences of the destructive and non-idempotent flags, making it highly transparent.

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?

Two sentences, each earning its place. The first states purpose and ties to the sibling; the second delivers essential behavioral caveats. No redundant phrasing, and the most critical information (purpose) is 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?

The description covers the core behaviors needed to call correctly: partial success, shared workspace, and the reference to the duplicate-domain rule. An output schema exists, so return value details are covered. It could mention the exact format of the `accounts` parameter, but the schema handles that. The only minor gap is not spelling out when to choose this over the bulk update tool, but given the sibling list and the clear 'create' verb, it's sufficient.

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%, so the schema already documents all three parameters (accounts, run_dedupe, append_label_names). The description does not add parameter-level details beyond mentioning 'several accounts' and 'per record,' which aligns with the accounts parameter. Baseline 3 is appropriate since the schema carries the semantic load.

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 clear verb-object statement — 'Create several accounts in one call' — and immediately distinguishes it from the singular `post_apollo_accounts` by referencing the same rule but for bulk. It unambiguously identifies the resource and operation.

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?

It explicitly frames the tool as the bulk counterpart of `post_apollo_accounts` and warns about partial success, which informs when to use it (multiple records) and what to expect. It doesn't explicitly say 'use this instead of the singular version when you have many accounts,' but the context strongly implies it. No alternative tools are named beyond the singular one, which is sufficient given the sibling list.

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