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

Annotations already flag destructive, open-world, non-idempotent behavior, yet the description goes further by enumerating exactly which command categories trigger an approval gate and how to route slow work via `background`. This is precisely the extra context (approval friction, execution mode) that annotations cannot express.

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?

Three tight sentences, front-loaded with what the tool does, then approval behavior, then the background hint. No filler and no repetition of the schema.

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 CLI wrapper with no output schema and covered safety annotations, the description delivers what an agent needs to invoke it correctly: execution context, approval triggers, and backgrounding. It omits any hint about output/error surfacing, which is a minor remaining gap.

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 67%, with `background` carrying no schema description at all; the description compensates by explaining when to set it true. The `args` example illustrates the expected array shape, though `why`/`site`/`server`/`approval_id` are left entirely to the schema.

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: 'Run wp-cli as the site's owner with --path set', with a concrete argument example (['plugin', 'list']). This clearly separates it from the generic `run` and the `magento` sibling, though it doesn't explicitly say when to prefer this over `run` or `db_query`.

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?

Gives real routing guidance: listing and checksum commands run immediately, while deletes, db reset/import, non-dry-run search-replace and eval require approval, and slow commands should set background=true. That tells the agent what to expect and how to invoke per command class, but it never names an alternative tool to use instead.

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