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

Beyond the annotations (destructiveHint=true, idempotentHint=false), the description explicitly explains the non-idempotent behavior: calling with the same term twice creates two keyword rows. It also states that the 'tracked set' is modified. This gives the agent useful behavioral context that goes beyond simply labeling the operation as destructive or non-idempotent.

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 extremely efficient: two sentences, no redundancy, and the core action and critical caveat are front-loaded. Every sentence adds meaning, with the non-idempotence warning coming right after the action.

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?

The description is complete for an agent to understand safety and correctness implications: it warns about duplication, confirms mutation, and references the tracked set. The presence of a full schema with 100% parameter coverage and an output schema avoids the need to describe return formats or optional parameters. Minor missing context is that 'explicit confirmation' is not sourced, but that is more of an external workflow step.

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 the schema already documents all four parameters. The description adds only light semantic detail about 'the same term' behavior, which reiterates the searchTerms concept. There is no need for additional parameter explanation, placing it at baseline.

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 uses a specific verb-resource pair ('Add a new tracked keyword to an Appskyline app') and clearly differentiates itself from siblings like delete_keyword and list_keywords through the action 'add' and the object 'tracked keyword'. It is immediately obvious what the tool does and how it differs from related 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?

The phrase 'after explicit confirmation' provides a necessary operational condition, and the context of adding a tracked keyword implies when it should be used. However, it does not explicitly mention when not to use it or name alternatives such as list_keywords or update_keyword-like operations, leaving some routing to inference.

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