Update settings

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

With no annotations provided, the description carries the full burden, and it discloses the key operational facts: privileged access ("Superuser only"), the mutating nature of the operation ("Bulk update"), and the partial-update semantics (providing only changed sections implies unspecified ones are left intact). It omits the return value and error behavior, but the most decision-relevant traits are covered and nothing contradicts the (absent) annotations.

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?

The purpose is front-loaded in the first sentence, followed by the usage rule, examples, and permission note. The examples are lengthy but earn their place because the open schema would otherwise leave the agent guessing at valid payload structures; there is no 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 single-parameter tool with an open schema, no annotations, and no output schema, the description covers everything needed to invoke it correctly: what `data` should contain, the partial-update rule, and the superuser requirement. Minor gaps remain — no mention of the response format or whether changes take effect immediately — but nothing critical for a correct call 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?

The schema's only property, `data`, is described as "Partial settings object..." but is otherwise completely open (`additionalProperties: {}`), so the schema carries almost no structural meaning. The description's three concrete examples (meta, smtp, batch with nested fields) are the sole documentation of what sections actually exist and what shapes they take — an enormous addition 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?

"Bulk update instance settings" states a specific verb (bulk update) and resource (instance settings), so an agent immediately knows what the tool does. It does not explicitly differentiate from siblings like get_settings or batch, relying on the name and verb to carry that distinction, which keeps it at 4 rather than 5.

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 instruction "Provide only the sections you want to change in `data`" gives clear, actionable context on how a caller should construct a request, and the first sentence establishes when to use it (modifying instance settings). However, it never names alternatives or exclusions — e.g., it does not point to get_settings for reads — so it lacks explicit when-not-to-use guidance.

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