call_provider_tool

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses the return shape ('provider's own result, plus a run_id'), the forwarding behavior ('Arguments are forwarded untouched'), the side effect of logging ('tool and its arguments go to the run log'), the scope boundary ('touches no other account'), and the no-model behavior. This gives an agent a complete safety and side-effect picture before calling.

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 six sentences, each earning its place: purpose, return value, sourcing guidance, scope, logging, and compatibility. It front-loads the core action in the first sentence and avoids any redundant re-statement of schema fields.

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 4-parameter tool with no output schema and no annotations, the description is remarkably complete. It explains the return value, the run log side effect, how to source parameters, and the environment in which the tool works, leaving little an agent needs to infer. The only thing absent is explicit sibling routing, but that is already covered under usage guidelines.

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 already describes all four parameters with 100% coverage, so the baseline is 3. The description adds meaningful guidance beyond the schema by directing the agent to source `tool` and `arguments` from `list_provider_tools` and by clarifying that `client` scopes the call to exactly that one account. This extra semantic guidance earns a 4.

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 a specific verb and resource: 'Call one of a provider's own tools with one client's credentials.' This clearly distinguishes it from sibling tools like call_provider_api (which would target the provider's API) and work_on_client (which is broader), by narrowing to a single client's credentials and a provider-defined tool. The first sentence alone makes the tool's job unmistakable.

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 clear context for when to invoke: it specifies acting on one client, using a provider's own tool, and notes 'No model is involved, so this works with agents off.' It also tells the agent to obtain `tool` and `arguments` from `list_provider_tools` rather than guessing, which is actionable guidance. It does not, however, explicitly name alternatives or state when not to use this tool, so it stops short of a 5.

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