replace-setting

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers the critical non-obvious trait: omitting any attribute from the request resets it to its original state. This is exactly the kind of destructive gotcha an agent needs to know before calling. It doesn't cover idempotency or response behavior, but the core hazard is explicit.

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?

Two short paragraphs with no filler: purpose in the first sentence, and the critical reset warning visually isolated under a bold 'Important:' header. Every sentence earns its place and the most important information is front-loaded.

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?

The description covers the replace/reset trap well and the schema fills in the fields, but with no output schema, no annotations, and a sibling set containing the confusingly similar replace-setting-value and update-setting-value, the missing disambiguation is a real gap. An agent could reasonably pick the wrong sibling without clearer routing.

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 already documents settingId and every requestBody sub-field (name, hint, tags, order, isJson) with individual descriptions, so the description need not restate them. Its added value is explaining the consequence of omitting fields — they reset — which is meaningful semantic context beyond the schema, though it stops short of providing concrete request-body examples.

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 opens with 'replaces the whole value of a Feature Flag or Setting identified by the settingId parameter' — a specific verb, resource, and scope. The 'complete replace' framing differentiates it from the sibling update-setting, but it doesn't disambiguate from the similarly named replace-setting-value, which also centers on 'value'.

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 bolded Important note — 'Not listing one means it will reset' — implicitly tells the agent this endpoint is for full replacements rather than partial edits, so an agent can infer not to use it for single-attribute changes. However, it never explicitly names alternatives like update-setting or replace-setting-value, leaving selection to inference among roughly 70 siblings.

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