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

The description adds 'Owner only,' a permission-based disclosure beyond what the annotations (destructiveHint: true, readOnlyHint: false) provide, which is genuinely useful. However, it stops short of disclosing what happens upon removal (e.g., access revocation, cascade effects on highlights or documents shared with that member). The annotations carry the safety profile, and the description contributes the authorization context, but behavioral details are still thin.

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?

Two short sentences: 'Remove someone from a shared trip. Owner only.' The most critical information is front-loaded in the first four words, and every word serves a purpose. There is zero fluff or redundancy.

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 simple two-parameter mutation with no output schema, the description covers the essential purpose and access rules adequately. Gaps include no connection to related operations (e.g., how it differs from `leave_journey`) or post-removal effects, but given the tool's simplicity, the description meets the minimum bar. It's mostly complete but doesn't exceed expectations.

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?

With 0% schema description coverage and no parameter context in the description, the agent must infer that user_id refers to the member being removed and journey_id to the shared trip. The parameter names are common enough to be guessable, but given the low coverage, the description should have compensated per the rubric. The 'Owner only' hint does imply user_id is not the owner, adding slight disambiguation, but that's a stretch to count as meaningful parameter guidance.

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 the specific verb 'Remove' with the resource 'someone from a shared trip,' clearly identifying the action and target. The qualifier 'Owner only' adds a useful access constraint. While it could more explicitly contrast with the sibling `leave_journey` tool, the action and resource are unambiguous and distinguishable.

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?

'Remove someone' implies a distinction from self-removal, but no explicit alternatives or when-not-to-use guidance is provided. The ownership condition is stated but the description doesn't tell the agent when to choose this over `leave_journey` or `delete_journey`. Context for when another tool would be more appropriate must be inferred from sibling names.

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