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

Even though readOnlyHint, idempotentHint, and destructiveHint are already provided, the description adds meaningful behavioral detail: rates are percentages, null when nothing was checked, pending states during checks, and a failure mode with an activation link when the add-on is not active. This goes well beyond the 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 long but densely packed with non-redundant information: purpose, outputs, parameter behaviors, failure conditions, read-only nature, and sibling distinction. Every sentence carries useful operational meaning, and the main purpose 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?

The tool is complex with four optional parameters and a rich output, yet the description covers all relevant behaviors, defaults, failure modes, and parameter effects. It also handles the multi-website case by referencing get_account. Nothing an agent needs to decide whether and how to call the tool is missing.

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 100%, so parameters are already documented. The description adds value by explaining the effect of parameters on the output, e.g., 'Pass surface to restrict every number to one platform' and 'include_answers=true for the latest answer text per prompt.' This provides semantic context beyond the bare schema descriptions.

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 opens with a specific verb and resource: 'Reads the AI Visibility dashboard of the website: how often AI assistants... mention and cite the brand.' It clearly states what data is returned and distinguishes itself from siblings, notably saying it is not Google Search Console data and pointing to get_keyword_rankings for that.

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 includes explicit usage guidance: when to pass surface, include_answers, and website_id, and that the tool cannot add prompts or competitors. It explicitly routes the user to get_keyword_rankings for Google Search Console data, making the when-not-to-use case clear.

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