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

Annotations already declare a safe read, and the description adds genuine behavioral context: historical ENABLED/PAUSED/ARCHIVED states remain queryable, PAUSED is not a writable target state, ARCHIVED is terminal, and negative targets support neither bids nor performance metrics. These are non-obvious constraints an agent cannot infer from the schema or annotations.

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 dense sentences, front-loaded with what is returned before the state/downstream constraints. The field enumeration is somewhat verbose given an output schema exists, but nothing is filler.

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 annotations, full schema coverage, and an output schema present, the description covers the remaining burden — state lifecycle, mutability constraints, and downstream workflow. An agent has everything needed to select and invoke it correctly.

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 description coverage is 100%, so all ten parameters (storeId format, limit cap, targetType semantics, asin/keywordText validity constraints) are already documented in the schema. The description adds no parameter-level syntax or filtering detail beyond that, so the 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 and resource (returns paginated negative keyword / negative ASIN records) and enumerates the fields returned, so an agent can distinguish it from query_advertising_targets (positive targets) without opening either schema. The closing note that negative targeting entities lack bid actions and performance metrics further separates it from sibling targeting tools.

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 gives clear downstream context — results feed AD_TARGETING_CHANGE to re-enable PAUSED or archive PAUSED/ENABLED entities, with PAUSED not writable and ARCHIVED terminal. It does not explicitly name when to prefer this over query_advertising_targets or how to choose negativeKeyword vs negativeAsin beyond the schema, so no exclusions are stated.

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