add_tracked_prompts

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

Annotations only include a title with no safety hints (readOnly/destructive). The description adds some behavioral context by specifying the required 'text' field and the expected object shape, and mentions that structured errors may be returned and that retrying is possible. However, it does not disclose side effects like deduplication, overwrite behavior, or rate limits, so the description does not fully carry the burden given no 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 well-structured with a clear opening purpose sentence, an expected-shape example, mapping guidance, and an args section. It is front-loaded and every sentence contributes value, though the args section somewhat repeats the shape explanation. Not overly verbose, but a bit longer than strictly necessary.

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 has no output schema and the description does not mention return values. It covers the main input format well, but omits the config parameter entirely and provides no operational constraints (e.g., batch size, duplicate handling). Given the tool's complexity (3 params, nested objects), the description is adequate but not fully complete.

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?

The schema has no descriptions (0% coverage), so the description compensates by explaining project_id as the project UUID from list_projects or create_project, and thoroughly describes the prompts array with a detailed object shape including required and optional fields. However, the config parameter is not mentioned at all, leaving a gap.

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 'Add AEO prompts to track for a project' with a parenthetical explaining what AEO prompts are (questions sent to AI answer engines). This gives a specific verb and resource, and it is clearly distinguished from sibling tools like add_tracked_keywords and the aeo_* generation/audit 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 description gives clear context on when to use this tool: when adding prompt objects for tracking. It provides explicit instructions on how to shape prompts and how to map columns from a sheet/CSV. However, it does not explicitly mention when not to use it or name alternative tools, so it lacks exclusions.

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