splitwise_delete_friend

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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses the write gate (SPLITWISE_ALLOW_WRITES=1), the underlying endpoint, the critical quirk that Splitwise returns HTTP 200 even when it refuses so success must be read from the body, that there is no undelete, and how 404 should be interpreted. This is exactly the extra context annotations cannot carry.

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?

Sections are clearly labeled and front-loaded with the destructive/write-gate warning first, which is the right priority. It is longer than strictly necessary — the Examples block largely restates the schema's own example — but no section is filler.

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 destructive, gated, non-idempotent-in-practice mutation, the description covers preconditions, failure modes, refusal handling, and recovery (re-add via splitwise_create_friend). Return values are also summarized even though an output schema exists, so nothing an agent needs to call this safely is missing.

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 reported as 0%, though the single friend_id property does carry an inline description. The description reinforces that the parameter is the friend's user id, supplies a concrete example ({"friend_id": 4821}), and adds error semantics tied to the id (404 means the id is not a friend). With only one parameter this is close to fully covered, but it stops short of adding format constraints beyond the schema.

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 opening line states a specific verb and resource ('Remove a friendship (unfriend a user)'), and the surrounding text makes clear it operates on the friend relationship rather than group membership. An agent can distinguish it from splitwise_remove_user_from_group and splitwise_create_friend without opening either schema.

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?

Explicit 'When to Use' and 'When NOT to Use' sections name the exact alternatives for adjacent intents: splitwise_remove_user_from_group for group removal, splitwise_create_expense for settling balances, and splitwise_resolve_friend / splitwise_get_friend when the id is uncertain. Routing conditions are fully specified.

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