bing_plan_add_site_roles

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

The description goes beyond annotations by clarifying that the tool sends nothing and records only intent, even though readOnlyHint is false. It also discloses what the result should be—plan id plus CLI apply command—which prevents the agent from assuming the change was already executed.

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 compact but information-dense. Each sentence contributes something distinct: purpose, execution semantics, and output behavior. There is no unnecessary fluff.

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 tool that records intent rather than executes a change, the description covers the main usage caveats and return values well, especially with no output schema. It doesn't explain why all six required parameters are needed, but the surrounding context and parameter names offset that somewhat.

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 0% and the description does not add any parameter-level meaning. While the parameter names are somewhat helpful, the description does not clarify important details such as what delegated_url is for, how authentication_code is used, or the relationship between is_administrator and is_read_only.

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 clearly conveys that the tool prepares a change for human review and only records intent, but it never explicitly names the resource being changed (site roles). It relies on the tool name to tell the agent what 'this change' is, so it is a little vague on its own.

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 explains when it should be used: when an agent should record and defer a change rather than apply it. It also gives follow-up guidance not to claim the change was applied, which is useful context for an agent trying to decide how to handle the result.

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