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

With no annotations, the description carries the full burden and does reveal important behavior: changes skip historical backfill, automatic mode is bounded by user scope, allow_private opts into provider processing of private data, and a current revision is required. These go beyond a simple 'updates policy' statement and help the agent anticipate side effects.

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 compact and front-loaded with the core purpose, with each additional sentence adding a distinct constraint or behavioral note. The phrasing is dense and somewhat fragmented, but there is no filler or redundant restatement.

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?

This is a seven-parameter policy mutation with no output schema stub and no annotations. The description supplies crucial policy behavior but still omits mode semantics, feature options, the source of the current revision, and the interaction between connection/authorization and private calls. A capable agent could not fully and confidently invoke it from this definition alone.

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 43%, so the description must compensate. It explains allow_private and automatic behavior, but it leaves several required parameters under-explained: the meanings of off/shadow/suggest, the intended values for features, what authorization should be, and how to obtain/current revision. The agent still has to guess at key inputs.

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 clear action ('opt in or out') on a resource ('semantic features') and adds that it operates under existing user authorization and scope. It reads as an update/configuration tool and can be distinguished from the read-only sibling semantic_status, though it does not explicitly name an alternative.

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 provides preconditions such as 'use current revision' and 'existing user authorization,' but it gives no explicit guidance about when to use this tool versus alternatives. No sibling tool is named, and there is no when-to-use/when-not-to-use framing.

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