work_on_client

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

The description explicitly mentions that changes are written to the run log and can be monitored, which discloses side effects. It also states the tool 'can act' and is the 'write within' counterpart, making its mutating nature apparent. No annotations are present, so this disclosure is important and sufficient.

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 overly metaphorical and poetic, using phrases like 'read across, write within' and 'open the control room to watch.' While not extremely long, it obscures the straightforward purpose and would benefit from a more direct, concise description.

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?

The description places the tool in context relative to its sibling `ask_across_clients` and mentions the run log for monitoring. It does not explicitly relate to other siblings like `call_provider_tool`, but the purpose and scope are sufficiently clear for typical usage.

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 input schema provides clear descriptions for both parameters, including an example for `request` and a note about scope for `client`. The tool description adds a bit of extra context by saying 'naming them is what unlocks it,' which reinforces the `client` parameter's role.

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 the tool acts on a single client's accounts using their tools, and explicitly contrasts it with the read-only `ask_across_clients` sibling. While the phrase 'Do something' is vague, the name and context make its role clear as the write/action counterpart for one client.

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 clearly differentiates this tool from `ask_across_clients` by stating that one is read-only across clients and the other can act on a single client. It also implies the client must be named, and that the agent has sessions only for that client, guiding when to use it.

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