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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write nature is covered. The description usefully adds deduplication ('already saved are skipped') and the side effect of triggering an analysis run, which annotations do not convey. However, it states the run unconditionally while the schema exposes an optional runAnalysisNow flag, creating ambiguity about whether the run is controllable.

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?

Two short, front-loaded sentences with no filler: the action first, then the dedup and run side effects. Only the vague 'one analysis run' phrasing costs it a point.

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?

Annotations cover the safety profile and there is no output schema to explain, but with a nested prompt array, a required context/llm_model analytics pattern, and a 40% schema coverage, the description leaves real gaps. It says nothing about the analysis-run toggle or what the caller gets back when prompts are skipped.

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 only 40%, so the description must compensate and largely does not: runAnalysisNow, advertiserProjectId, and the prompt item fields (location, funnelStage, languageCode) are never explained. The description only gestures at 'prompts' and never clarifies that runAnalysisNow governs the analysis run it mentions.

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?

States a specific verb and resource ('Add tracked AI Visibility prompts') plus a scope distinction: existing prompts are skipped, so it reads as a bulk/upsert-style add. It does not explicitly say how it differs from the sibling 'add-llm-prompt', which an agent must infer from the plural 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 skip-if-already-saved behavior implies a safe 'just add what's new' context, but there is no explicit when-to-use guidance or reference to alternatives like add-llm-prompt or bulk-add-monitored-articles. The absence of any mention of runAnalysisNow also leaves the caller without a decision rule for that toggle.

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