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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds real behavior beyond that: the list is inert until attached, exact duplicate keywords are silently dropped, and the name must be unique among the account's negative keyword lists. It does not cover failure modes (e.g. duplicate name error) or permission requirements, so it is strong but not complete.

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 one-line purpose, then scope, then args. Every paragraph earns its place except the Returns block, which partly restates what the output schema already provides. Dense but not padded.

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?

With an output schema present, the description need not explain return values, and it still summarizes them briefly. Combined with annotations and full param documentation, an agent has everything needed to construct a correct call and knows what to do next with the resulting list.

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 0% and the schema types keywords as an untyped object map, so the description carries the entire burden. It documents all three parameters: customer_id format ('numbers only, no hyphens'), name constraints (unique, 1-255 chars), and keyword structure with text plus match_type values EXACT/PHRASE/BROAD and a BROAD default — information that exists nowhere in the schema.

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?

Opens with a specific verb+resource ('Creates a shared negative keyword list, optionally with its keywords') and immediately defines what a shared list is versus the per-campaign/account negative tools in the sibling set. An agent can distinguish this from add_negative_keywords and attach_negative_keyword_list without opening any schema.

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 states the key usage fact ('The list does nothing until it is attached') and names attach_negative_keyword_list, add_to_negative_keyword_list and remove_from_negative_keyword_list as the follow-up paths. It stops short of a decision rule versus account-level or campaign-level negative tools, so the when-not guidance is implied rather than stated.

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