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

Annotations already declare destructiveHint=true, but the description goes further by specifying the exact nature of destruction: 'deletes the membership record outright with no undo,' and clarifies the matching behavior ('matching the first record found'). It also discloses the return format ({message, email}) and the full set of failure conditions, including permission and scope requirements. This adds substantial context beyond the structured annotations.

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 sentences carry a high density of information with no filler. The purpose is front-loaded in the first clause, followed by the destructive nature and return format, then error conditions and owner restriction. Every sentence earns its place, and the structure is logical and scannable.

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 with two parameters, no output schema, and annotations already marking destructiveness, the description covers everything an agent needs: the exact operation, the two accepted identifiers, the matching rule, the return shape, the irreversibility, the error triggers, and the permission requirement. It even provides the recovery path via invite_member. There is no missing information that would impair correct invocation.

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 100% and each parameter already has a clear description, so the baseline is 3. The description adds value by explicitly stating that the two parameters are alternatives ('by memberId or email') and that the removal targets the first matching record, which clarifies the semantics of both parameters beyond their individual schema entries. This extra nuance justifies a score above baseline.

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 a specific verb ('Remove') and resource ('member') with precise scope ('from this project'), and distinguishes itself from siblings like invite_member and list_members by focusing on removal. It clearly identifies the two alternative identifiers (memberId or email) and notes it matches the first record, so an agent can differentiate it without opening other tool definitions.

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 gives explicit error conditions that double as preconditions: it fails if neither identifier is provided, no match, caller isn't owner, or token lacks config scope, and it explicitly states 'Owner only.' It also hints at the alternative by noting that getting the person back requires a fresh invite_member call, which tells the agent when to choose that tool instead. However, it does not explicitly contrast with set_member_role or other membership tools, so it stops short of full when-not guidance.

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