use

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

Without annotations, the description carries the full burden and fully discloses the persistent side effect: 'will target the selected database's daemon until changed again.' It also reveals the conditional no-op behavior under remote targets, which is a critical behavioral nuance beyond a simple switch.

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 well-structured with a front-loaded purpose, followed by behavioral scope, a limitation caveat, and a clear Args block. Every sentence contributes unique information—no filler or redundancy—making it appropriately sized for the tool's simplicity.

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 one-parameter tool with an output schema present, the description is complete: it states the operation, the effect on subsequent tools, the local-only limitation, and the parameter format. Return values are presumably covered by the output schema, so no additional explanation is needed.

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?

The schema provides only a 'string' type for 'name' with no description, leaving 0% coverage. The description compensates by explaining: 'Database name (e.g., 'coding', 'work'). Use 'default' for the default database,' adding examples and special-case instructions that make the parameter's meaning and usage unambiguous.

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 opens with 'Switch to a different named database for subsequent operations,' which is a specific verb and resource that clearly distinguishes this tool from siblings like find, ingest, or sync. It establishes the tool as a context setter, not a data operation, and the title 'use' is adequately expanded.

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 explains that 'All tools (find, ingest, sync, etc.) will target the selected database's daemon until changed again,' providing clear guidance on when to invoke it. It also notes the exclusion: 'while a remote target ... is active, the remote daemon is fixed to its own database and this has no effect,' and suggests using list(kind='databases') to inspect the current state.

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