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

Annotations declare destructiveHint=true, and the description strongly reinforces this with 'Remove someone' and warns it only works if they aren't on any expense yet. The description adds valuable context about the constraints (read-only secure splits, simple/accountless split limitation) that go beyond what annotations provide. It doesn't contradict annotations; it complements them with important behavioral specifics.

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, all carrying meaningful information with no padding. The description is efficiently front-loaded with the core action ('Remove someone from a split') followed by constraints. No wasted words.

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 mutation tool with destructiveHint and readOnlyHint=false, the description covers the key constraints: the prerequisite (not on any expense), the split type limitation (simple/accountless), and secure split behavior. The output schema exists to describe return values, and the 2 params are fully documented in the schema. This is a complete picture for the agent.

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% for both parameters (split and participant), each with clear descriptions. The description reinforces which objects are involved and the constraints (removal is restricted), but the schema already documents the parameter semantics well. The description adds the eligibility nuance for the participant parameter by stating the 'not on any expense' condition.

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+resource ('Remove someone from a split') and immediately differentiates from siblings by noting it works only on accountless, simple splits and that secure splits are read-only here. This distinguishes remove_participant from similar mutation tools like rename_participant and add_participant.

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 clear usage context: 'Only works if they aren't on any expense yet' states a runtime precondition, and 'Secure splits... are read-only here and must be opened in a browser' explicitly tells the agent when NOT to use this tool. This is explicit when/when-not guidance with clear boundaries.

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