growsurf_create_campaign_reward

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

All annotations are neutral false values, so the description carries the behavioral disclosure burden. It adds meaningful behavior beyond annotations: the write side-effect of creating, the type-compatibility constraint, and the fallback default-campaign targeting. No contradiction exists between the 'Create' action and readOnlyHint=false. It stops short of describing output/error behavior, but for a creation tool this covers the key decisions an agent must make.

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?

Three efficient sentences with zero filler. Purpose is front-loaded, with the compatibility constraint and targeting behavior placed after. Every sentence earns its place, and the most decision-critical info (type constraint, target default) is captured before the agent starts filling parameters.

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 high-complexity tool with 22 parameters, nested objects, and only 18% schema coverage, the description covers only the two most critical decisions (type compatibility and target selection). The output schema covers return values, which helps, but the wide semantic gaps across the reward-type-specific fields (MILESTONE, LEADERBOARD config, commissionStructure, value tax fields) are left to the sparse schema. Adequate but incomplete for the complexity.

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 is expected to compensate for the 22 parameters. It adds real value on `type` (the compatibility constraint with program type, which is not in the schema) and reinforces `campaignId` targeting. But it ignores the remaining ~20 parameters (limit, order, value, commissionStructure, isVisible, etc.), many of which the schema also fails to describe. The description meaningfully helps on 2 params but does not compensate for the low overall coverage.

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?

Opens with a specific verb+resource pair ('Create a new campaign reward') that clearly identifies a creation operation. This distinguishes it from the sibling CRUD tools (update/delete/list campaign rewards) without requiring the agent to open any schema.

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 on campaign targeting ('Targets campaignId if you pass it, otherwise GROWSURF_CAMPAIGN_ID') and the type-compatibility rule (affiliate vs referral programs). However, it never explicitly routes between alternatives — e.g., it doesn't say when to create vs update a reward, or how this relates to growsurf_create_campaign. The when-not-to-use guidance is implied but never stated.

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