Update settings

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

Annotations already declare non-destructive, idempotent, non-open-world writes, so safety is covered. The description usefully adds merge semantics ("only the keys you pass change"), but that phrasing is potentially misleading for nested objects such as `alerts`, whose subfields are all required and would be replaced wholesale — a behavioral nuance an agent needs and the description does not surface.

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 clauses, zero filler, with the merge rule and the sibling exclusion both front-loaded. Every word earns its place.

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 rich nested-object mutation with strong annotations and a well-annotated schema, the description covers the two things structured data cannot: merge behavior and the set_ai_provider boundary. The remaining gap is nested-object replacement semantics, which is a real risk given `alerts` requires all four subfields.

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 single top-level `settings` parameter carries no schema description (coverage reported as 0%), but every nested property is documented with enums, ranges and purpose in the schema itself. The description adds only the merge rule and no key-level guidance, so it neither compensates for nor duplicates the schema meaningfully.

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?

Names a specific verb and resource ("Change app settings") and adds the crucial partial-update qualifier "only the keys you pass change". It differentiates itself from one relevant sibling (set_ai_provider), though other adjacent settings-ish siblings like update_project or set_project_markets are not addressed.

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 routes the AI provider/model case to set_ai_provider, which is the most likely mis-invocation given a settings tool. No statement of when not to use it beyond that one exclusion, and no note about prerequisites or whether a read-back is needed.

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