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

Beyond the annotations (not read-only, not destructive), the description adds meaningful behavioral context: it states the partial-update behavior ('Only the fields you pass are changed'), which is a key behavioral trait not captured by annotations. It also discloses the read-only restriction on secure splits. The only gap is not describing response output, but an output schema exists so this is not required. Credit given for the partial-update and scope behaviors.

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 tight sentences covering purpose, behavior, and exclusions without fluff. Front-loaded with the core action. Every sentence earns its place; no redundancy with schema or annotations.

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 9-parameter mutation tool, the description covers the essentials: what it does, partial-update behavior, id sourcing, and the secure-split caveat. With an output schema present and 89% schema parameter coverage, the description adequately bridges the gaps. Could mention prerequisites like split ownership, but the secure-split caveat substantially covers the main restriction. Minor gap is not listing all editable fields, but schema handles that.

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 89% (high), so the schema itself documents parameters well. The description adds the partial-update semantics that clarify which parameters are optional overrides. It doesn't add per-parameter detail beyond what the schema provides (e.g., date format, shares semantics are already in schema). Baseline 3 is appropriate given the high schema coverage.

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 clearly states the verb (change/update), the resource (existing expense or payment), and the scope (only fields passed are changed). It distinguishes from siblings by noting it works on simple, accountless splits, and explicitly frames it as the update counterpart to add_expense/record_payment and a companion to get_split. Strong purpose statement.

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?

Explicitly states when to use: to modify an existing expense/payment. Provides critical exclusions: secure splits (created by signed-in user) are read-only here and must be opened in a browser, implying use of get_split or browser for those. Tells where ids come from (get_split). This is robust when/when-not guidance for a mutation tool.

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