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

Annotations already declare destructive=true, idempotent=true, readOnly=false, but the description adds genuinely non-obvious behavior: a conditional cascade that removes the client business membership if this assignment created it, and the owner-only restriction on unassigning admins. It does not describe failure modes (e.g. what happens if the membership pre-existed or the user is not assigned), but the cascade disclosure is the key extra context.

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?

Three short sentences, each carrying distinct information: the action, the cascade side effect, the permission gate, and the scope boundary. The core action is front-loaded and nothing is redundant.

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?

An output schema exists so return values need no explanation, and the description covers the destructive nature, the cascade, and authorization requirements — enough to call it safely. The only gap is the absence of an explicit pointer to the sibling revoke/assign tools for adjacent scenarios.

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 description coverage is 100%, so all three parameters (userId, partnerId, businessId) are already documented in the schema with their roles. The description adds no per-parameter meaning such as ID sourcing or format constraints, so the baseline 3 applies.

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?

States a specific verb and resource — removes a staff member's agency assignment to one client business — and adds a boundary statement ('does not remove the person from the agency') that separates it from a full member revocation. It stops short of naming the sibling tool (e.g. agency_profile_revoke_member) that an agent should pick for the broader action.

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?

Provides useful preconditions — requires an agency owner or admin, and only the owner can unassign an admin — which tells the agent when the call will succeed. However, it never explicitly states when to choose this over agency_profile_revoke_member or agency_profile_assign; the distinction is only implied by the negative scope clause.

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