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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'without modifying it' mostly restates structured data. The genuinely additive content is the authorization note that employee reports require employees.read, which annotations do not cover; however, nothing explains what a preview actually produces (sample rows? rendered layout? evaluation of the data overrides?).

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 sentences with the core scope front-loaded and no filler. The permission clause is appropriately placed last as a conditional caveat.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile. Still, for a tool whose distinguishing input is an arbitrary override object, leaving its purpose and effect unexplained leaves a real hole in what an agent needs to call it correctly.

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 description coverage is 50% and the undocumented half matters most: the free-form 'data' object is the mechanism for previewing with alternative inputs, yet the description never mentions it or how it is applied. The schema's own text for 'data' is generic boilerplate ('read the tool description and existing record before editing') that this description fails to fulfill.

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 ('Preview') and resource ('a saved report') plus a scope constraint ('without modifying it'), which separates it from get_report, export_report and list_reports. It stops short of saying how a preview differs from a plain read or an export, so an agent still has to infer the distinction from sibling names.

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?

Usage is only implied: 'without modifying it' hints this is the safe, non-persisting route while export_report and export_* handle output generation, but no alternative is named and no trigger condition is given. The agent must guess when preview beats get_report.

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