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

Adds real value beyond the destructiveHint annotation: rank history is destroyed permanently, unscoped text fans out across all stores/countries, and unknown IDs cause an atomic batch rejection with no partial deletion. Does not mention any permission, rate-limit, or confirmation requirements for a destructive operation.

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 sentences, each carrying distinct information: what is deleted, how targets are selected, and the atomicity guarantee. The destructive consequence 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?

For a 5-parameter destructive mutation with an output schema available, the description covers the main behavioral risks an agent needs. The remaining hole is the interaction rule between the two selection arrays, which is the most likely source of a wrong call.

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?

With only 40% schema coverage the description must carry weight, and it does explain that selection comes from row IDs or text plus store/country scoping. However it never states whether keywords and trackedKeywordIds are mutually exclusive or what happens if both or neither are supplied, and projectId goes entirely unmentioned.

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 ('Removes selected tracked keywords') plus the irreversible side effect ('permanently deletes their rank history'). It does not explicitly differentiate from the sibling remove_keyword_competitors, so an agent must infer that this tool is the generic keyword remover while the sibling handles competitor lists.

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?

Gives concrete selection semantics — ID-based vs text-based, optional store/country narrowing, and the important default that unscoped text matches every store and country. Missing an explicit statement about when to prefer trackedKeywordIds over keywords (mutual exclusivity) and no reference to alternative tools.

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