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

The description goes beyond the annotations by spelling out the concrete consequence of non-idempotency: calling with the same term twice creates two keyword rows. This is valuable behavioral context beyond idempotentHint=false and destructiveHint=true, and it is consistent with those 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?

The description is two concise sentences with no filler. It front-loads the primary action and resource, then immediately conveys the most important behavioral caveat. Every sentence contributes necessary information.

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 mutating tool, the description covers the required confirmation, the state change, and the duplicate-row consequence. The input schema documents the parameters, and an output schema exists, so no essential guidance is missing for correct invocation.

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 parameters are already documented with clear semantics. The description adds no individual parameter-level detail beyond what the schema provides, which fits the baseline score of 3 for tools with complete schema coverage.

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 clearly states the action ('Add') and the specific resource ('a new tracked keyword to an Appskyline app'). It also distinguishes the operation from sibling tools like delete_keyword and list_keywords. The behavior is specific and not a tautology of the tool name.

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?

The description provides clear context by stating the tool should be used 'after explicit confirmation,' which is a meaningful precondition for a state-changing operation. It does not explicitly name alternative tools or state exact when-not conditions, but the intended use is nevertheless clear from the sibling context and the action itself.

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