growsurf_update_campaign_design

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

Discloses the partial-update behavior ('Only the fields you send are changed; anything you leave out is untouched') and the array-replacement caveat ('arrays replace wholesale'). This complements the destructiveHint and idempotentHint annotations by explaining exactly how mutation occurs. It also warns to preserve starter content, adding operational context beyond the annotations. No contradiction found.

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 description is moderately long but each sentence earns its place: purpose, update semantics, operational guidance, and targeting. It is front-loaded with the core action. While it could be tightened (e.g., merging related clauses), the structure is logical and scannable, with minimal redundancy.

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?

Given the tool's complexity (partial updates, nested objects, fallback target), the description covers the essential steps to invoke it correctly: fetch first, preserve content, pass fields, target campaign. An output schema exists, so return-value explanation is not required. The only minor gap is that it doesn't enumerate all possible subfields under `fields`, but the 'including' phrasing and reference to fetching configuration imply discoverability. Sufficient for a competent agent.

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 gives 50% coverage (only campaignId has a description). The description compensates for the undocumented `fields` object by explaining its purpose (pass fields to change), mentioning two specific subfields, and instructing to pass only desired fields. It also reiterates campaignId's default behavior, reinforcing the schema. This adds meaningful context that isn't in the schema, addressing the coverage 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?

The description clearly states the tool updates the design configuration of a GrowSurf program, naming specific subfields (login and payoutDestinationConfirmation). It distinguishes from siblings like growsurf_get_campaign_design (retrieval) and growsurf_update_campaign (general update) by targeting design-specific copy. The verb-resource pairing is explicit and unambiguous.

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?

Provides concrete usage steps: fetch configuration first, preserve starter content unless user requests change, pass only desired fields under `fields`. Explains targeting via campaignId with default fallback. While it doesn't explicitly mention when NOT to use this tool versus alternatives, the context of design configuration is clear enough to guide selection. Lacks explicit exclusions but the procedural guidance is strong.

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