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

Annotations already establish read-only, non-destructive, closed-world behavior, so the description's remaining burden is small. It adds the meaningful default that only enabled negatives are returned unless state is overridden, but it says nothing about pagination behavior or the shape of the result set for a 10-parameter list tool.

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 tight sentences, front-loaded with what is returned and immediately followed by the default-state and scoping behavior. No wasted clauses and no restatement of the tool name.

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?

Covers scope, defaults, ID provenance, and the profile requirement, which is enough to call a read-only listing tool correctly. The remaining gap is that no output schema exists and the description does not indicate the fields returned per negative entry or how limit/offset paging behaves.

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 80%, so the schema already documents kind, level, state, search, and ID provenance. The description repeats the same facts (state defaults to enabled, campaign_id/ad_group_id from get_campaigns/get_ad_groups, profile_id from list_profiles) rather than adding formats, enumeration values, or interaction between filters, so baseline 3 applies.

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+resource: browse existing negative keywords and negative product/category targets, at campaign and ad-group level. The word 'negative' plus the mention of campaign/ad-group scoping separates it from siblings like get_targets, though it never names the positive-target sibling directly.

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?

Implied usage is clear (browse negatives, optionally scoped by campaign/ad group), and it tells the agent where IDs come from (list_profiles, get_campaigns, get_ad_groups). It does not state when a different sibling should be used instead, or any exclusion such as not returning positive targets.

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