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

Annotations only declare it is a non-read-only, non-destructive write; the description adds substantive constraints beyond them — the currency becomes immutable after expenses exist, and splits created by a signed-in user are not editable through this path. It does not say what happens if neither title nor currency is supplied, or what the response contains, but with annotations already covering safety, this is well above baseline.

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, front-loaded with the action before the constraints. Each sentence carries distinct information — action, precondition, access-mode restriction. Minor deduction for the slightly loose phrasing "Works on simple, accountless splits," which requires inference about what makes a split accountless.

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 annotations cover the safety profile. What remains is a mutation tool whose description does cover the two decisive failure modes (currency already locked, secure split). The missing piece is the no-op case when neither field is passed and any error/permission behavior, which keeps it off a 5.

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 only 33%: `split` is documented (key or full URL) and `currency` carries an enum, but `title` has nothing beyond minLength. The description partially compensates by explaining the currency lock rule, which is genuine added meaning, but it says nothing about title constraints (uniqueness, length, trimming) or that title and currency are both optional and only `split` is required.

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?

Opens with a specific verb+resource+fields: "Change a split's title or currency." That clearly separates it from create_split, get_split, and update_entry without naming siblings — the mutation scope is unambiguous. The title ("Rename a split") is narrower than the actual behavior, but the description corrects it immediately.

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?

Gives an explicit exclusion: secure splits are read-only here and must be opened in a browser, plus a precondition: currency is locked once expenses exist. That is real when-to-use/when-not guidance. The only gap is that it never names an in-tool alternative (e.g., get_split to inspect state before mutating), so it stops just short of full routing guidance.

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