decideApplication

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

Annotations already indicate destructiveHint=true (destructive action) and idempotentHint=false. The description adds that it 'affects who can earn commissions,' but does not detail what happens on approval vs rejection or whether the action is reversible. This adds minimal extra transparency.

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 two sentences with no redundancy. It fronts the main purpose ('Approve or reject') and adds a single impactful consequence statement. 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 consequential tool with no output schema, the description lacks details on what happens after the decision (e.g., confirmation, error cases) or prerequisites (e.g., must have listAffiliateApplications first). It provides adequate but not comprehensive context.

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 100%, so the schema fully documents the three parameters. The description does not elaborate on them, especially 'reason,' which could benefit from context. Baseline score of 3 is appropriate.

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 specifies the action ('Approve or reject') and the resource ('affiliate's application to join your campaign'). It distinguishes this tool from siblings like listAffiliateApplications and joinCampaign by focusing on the decision-making step.

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 description implies this tool is for consequential decisions affecting commission eligibility, providing context for use. However, it does not explicitly state when not to use it or mention alternatives like listAffiliateApplications for review before deciding.

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