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

Annotations already declare destructive=true, openWorld=true, readOnly=false, and idempotent=false. The description adds useful context beyond those annotations: draft-only behavior, no runtime activation, preservation of tailored policies under starter defaults, empty answers allowed, and no invented defaults for missing facts. It does not explain overwrite semantics or concurrency behavior, but it meaningfully supplements the 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 purpose is front-loaded and most sentences add domain-specific guidance rather than filler. It is dense and slightly repetitive with the title, but appropriately sized for a complex policy-save operation.

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?

For a complex mutation with six parameters, no output schema, and low schema description coverage, the description covers important domain behavior but leaves out concurrency via expectedRevision, retry semantics for idempotency_key, permissions/auth expectations, and what the save returns or overwrites.

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 only 17%, so the description must compensate. It explains useStarterDefaults/catalogVersion, employeeId, owned selection references, source kinds, empty answers, and skipping questions, but it omits expectedRevision, company, idempotency_key, and most of the answer object structure.

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 states a specific verb and resource: saving a partial policy answer patch. It also distinguishes the operation from activation by saying 'Draft only, no runtime activation', which separates it from the publish sibling and makes the scope clear.

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?

It gives clear usage context for partial/draft saves, conditional guidance for useStarterDefaults and catalogVersion, employeeId for employee selection, and selection references for known destinations. It stops short of explicitly naming read/publish alternatives or required prerequisite reads, so it is strong but not fully explicit.

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