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

The description adds behavioral context beyond the annotations: it states execution is synchronous, task support is forbidden, and the returned JSON is internal application state for heavyweight orchestration. It also instructs how to present results (never raw JSON, mention IDs only when useful). These are meaningful behavioral disclosures that help the agent understand side effects and output sensitivity. The read-only claim matches the annotation, so there is no 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?

The description is not excessively long, but the opening sentence is tautological and adds no value. The subsequent sentences deliver useful usage instructions, but they are somewhat scattered, mixing classification, execution mode, and user-interaction guidelines. While each sentence is short, the overall structure weaves general orchestration policies into a tool-specific description, making it less crisp than it could be.

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?

Despite having an output schema, the description leaves critical gaps. It never states what the preview link looks like, what input identifiers are needed, or what operational prerequisites exist. With 11 parameters and no schema descriptions, the tool remains poorly documented. The note that the returned JSON is 'internal application state' is helpful but does not compensate for the missing parameter information and overall purpose clarity.

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?

With 11 parameters and 0% schema description coverage, the description carries a heavy burden to explain parameters, but it mentions none by name or meaning. It does not even identify the required 'previewId' or any ID relationship. The description is entirely silent on parameter semantics, leaving the agent to guess the purpose and constraints of each field.

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 begins with 'get preview link', which merely restates the tool name and provides no additional verb or object detail. It fails to specify what the preview link is for, what it contains, or how it differs from sibling tools like 'generate_preview_links' or 'preview_trafficking_output'. The rest of the description focuses on output handling instructions rather than clarifying the tool's core purpose.

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 no explicit guidance on when to call this tool versus alternatives. It mentions using 'assistantSummary first' and never displaying raw JSON, but these are general response-formatting rules, not usage conditions. No prerequisites, typical scenarios, or alternative tools are referenced, leaving the agent without decision criteria for selection.

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