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

Beyond the annotations it discloses non-obvious behavior: changes take effect immediately without a deploy, enabling the database restarts the lambda on its next request so migrations run, enabling the database yields an empty store, and deactivation is owner-only and destructive. This substantiates the destructiveHint and idempotentHint rather than restating them.

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?

Front-loaded with the purpose and sized proportionally to a tool with meaningful side effects, but the kind enumeration is buried in a long parenthetical with awkward phrasing ('off until switched on, which makes it, empty') that slightly impedes scanning.

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 two-parameter action tool with annotations covering the safety profile and no output schema, the description covers the kinds, timing of effects, restart/migration consequences, and the absence of an inverse operation — everything needed to invoke 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 coverage is 100%, so the schema already defines 'kind' and 'privateKey'. The description still adds real semantics per kind (defaults and side effects for database/secrets/workspace) that the flat schema strings do not convey, though it says nothing extra about the 'privateKey' editor key parameter.

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 precise verb+resource (switch on a kind of data) and then enumerates the three valid kinds ('database', 'secrets', 'workspace') with their default states, so an agent can distinguish this from siblings like set_secret or list_secrets without opening the schema.

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 explicit when-to-use criteria with concrete examples ('records need the database, an API key for a service it calls needs secrets') and an explicit exclusion ('There is no tool to switch one off: that deletes what it held, and is the owner's to do in the editor'), routing the agent away from an impossible action.

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