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

Annotations declare destructiveHint=true, and the description adds material context beyond that: changes are "Logged and undoable," which softens the risk profile an agent would otherwise infer. It also constrains value domains (percent 0–20, on/off, list format), though it says nothing about permission requirements or what a failed validation looks like.

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?

One dense, front-loaded sentence opens with the verb and the one-setting constraint before the enumeration, and the exclusion and undoability notes close it out. The long inline list is heavy but every item earns its place by documenting an enum value the schema does not describe.

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 two-parameter mutation with no output schema, the definition covers allowed keys, value formats, scope exclusions, and recoverability. What remains unsaid is the response shape and error behavior, which is acceptable given the absence of an output schema but leaves the agent slightly under-informed on failure handling.

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 0%, so the description must carry the burden, and it largely does: it explains per-setting value semantics (percent 0–20, on/off toggles, "up to 3, like [3,10]") that the bare anyOf/string enum cannot convey. Numeric settings like invoice_due_days and estimate_valid_days are listed without units or bounds, leaving a small gap.

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?

"Change ONE setting" gives a specific verb and resource, and the enumerated list of allowed setting keys makes the scope unambiguous. It does not name siblings such as get_settings or undo_action, so the agent must infer the read-vs-write split, but the exclusion of card/payment settings draws a clear boundary.

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?

"Change ONE setting" plus the explicit "Card fees and payment settings are never changeable here" tells the agent both the constraint (one key per call) and a hard exclusion. There is no explicit guidance to call get_settings first or to use undo_action for rollback, leaving some routing to inference.

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