growsurf_update_campaign_reward

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the mutation/intent is covered. The description adds value beyond annotations: it discloses that `type` is immutable (a real behavioral constraint an agent must respect) and explains the campaign targeting fallback logic. No contradiction with annotations — an update aligns with destructive+idempotent hints.

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?

Four sentences with zero filler, front-loaded with the primary action. The campaignRewardId example, the immutability constraint, and the targeting rule each earn their place. Not a full 5 only because it sacrifices a bit of guidance depth to stay this tight.

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?

An output schema exists, so return values are covered, and annotations handle the safety/idempotency profile. For a 22-parameter tool with nested objects, however, the description is thin: it never explains which fields apply to which reward types (e.g., commissionStructure being AFFILIATE-only is only hinted in the schema, not the description), nor whether update is a partial or full replacement of fields. The type-immutability disclosure is the most valuable signal, but the full field-applicability matrix is left to the 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?

Schema description coverage is only 18%, so the description carries a heavy obligation to compensate for the other ~82% of parameters. It only clarifies `campaignRewardId` (the reward key, e.g. crew_...) and the campaignId targeting rule. The many undocumented flat fields (limit, order, isVisible, couponCode, conversionsRequired, etc.) and most commission subfields receive no guidance from the description. The nested-object schema descriptions (value, referredValue, commissionStructure) are rich, but the description itself does little to bridge 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?

States a specific verb-resource pair ('Update an existing campaign reward (reward config)') and correctly frames it as operating on an existing reward, which distinguishes it from the sibling create/delete/list reward tools. It doesn't explicitly name those siblings, but the 'existing' framing plus the campaignRewardId key semantics makes the intent clear. Minor deduction for not naming the create/delete alternatives explicitly.

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 useful context: the reward `type` being immutable tells the agent what not to attempt, and the targeting rule ('Targets campaignId if you pass it, otherwise GROWSURF_CAMPAIGN_ID') explains when the campaignId param matters. However, there is no explicit guidance on when to use this tool instead of growsurf_create_campaign_reward or growsurf_delete_campaign_reward, or on how the many optional fields interact per reward type. Usage context is implied rather than stated.

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