ai_citation_track

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

Annotations declare readOnly, openWorld, non-idempotent, non-destructive. Description adds 'Paid + non-deterministic', 'results are directional and dated', and warns about API-UX discrepancies, providing behavioral context beyond annotations without contradiction.

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?

Description is a single cohesive paragraph that front-loads the core function. It's dense with useful information but could be slightly improved with structured formatting. Every sentence adds value with no redundancy.

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?

Description covers input (managed prompt set, brand, engines, samples, competitors, brand domains), process (sampling, confidence interval, share-of-voice, volatility), and limitations (directionality, datedness, API differences). With no output schema, it adequately explains expected results.

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%, and description adds valuable context for parameters: 'freeze it across cycles' for prompts, 'default 7 (>=7 recommended)' for samples, and 'Your domain(s) to detect in citations' for brand_domains, enhancing schema descriptions meaningfully.

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?

Description clearly states the tool tracks brand mention and citation share-of-voice across AI answer engines for a managed prompt set. It specifies the action (track), resource (brand mentions/citations), and scope (compared to competitors), distinguishing it from all sibling tools which focus on different domains like GSC, GA4, or Cloudflare.

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?

Description provides explicit context on when to use ('NOT an AI rank', 'single runs are statistically meaningless') and limitations (developer-API vs consumer UI, AIO has no API). It doesn't explicitly state when not to use or list alternatives, but the tool's uniqueness among siblings makes these implicit.

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