remove_site_role

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

There are no annotations, so the description carries the full burden for surfacing side effectscor. It discloses only that a BingWebmasterError is raised when removal fails. It does not state whether removal is destructive/permanent, whether the role object must match an existing role exactly, or how the user is identified (e.g., by Email in the site_role object).

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 a single front-loaded sentence followed by compact docstring fields. There is no redundancy or fluff; all lines serve a purpose (summary, args, raised error).

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 omits essential context for a destructive operation: how to construct/pass site_role, whether to fetch it first via get_site_roles, what success/failure responses look like, and whether this permanently removes the user's access. With no output schema and no annotations, an agent is left with an under-specified call contract.

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 'Args' section merely restates the parameter names: 'site_url: The URL of the site' and 'site_role: The site role to remove'. It does not explain the required shape of the SiteRole object (fields like Email, Role, Site), which is especially confusing since site_role is typed as a complex object in the schema. The description adds almost no meaning beyond what an agent can infer from names.

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 uses a specific verb and object: 'Remove a user's site role.' This clearly distinguishes the tool from its sibling tools get_site_roles and add_site_roles without needing to read further.

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?

No guidance is given on when to use this operation versus alternatives like add_site_roles, nor any prerequisites (e.g., fetching the role via get_site_roles first). The only implied usage is the action word 'remove', which is not enough for an agent to safely choose and invoke this tool.

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