Program Design Advisor

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds value beyond that: it discloses what the tool returns (short draft, complete benchmarkFacts, proposed configurationPlan, unresolved decisions), that incentive amounts stay unresolved without customer input, and that guidance falls back to documentation-based content when no bundle is present.

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?

Purpose and read-only nature are front-loaded, and most sentences carry signal (the decisions caveat, the mode distinction, the AFFILIATE and industry: other behaviors). It is a single dense block with several mode-specific clauses that could be broken into a tighter list, but there is little outright waste.

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 12-parameter, all-optional advisor with an output schema and full annotations, the description covers mode selection, return contents, fallback behavior, and key enum semantics. An agent has enough to call it correctly; only explicit routing against sibling creation tools is missing.

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?

With schema description coverage at 92%, the schema already documents nearly all twelve parameters, so the baseline is 3. The description reinforces a few semantics (programType: AFFILIATE selects affiliate advice; industry: other covers local services, pets, hospitality, agencies; currencyISO omits dollar bands for non-USD) but largely restates what the schema provides.

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 opens with a specific verb and resource set ("Generate program designs, benchmarks, typical rewards, and metric definitions, including participant-to-referral and lead-to-referral ratios") and immediately characterizes the artifact returned. It is clearly an advisory/planning tool, distinguishable from the many sibling mutation tools like growsurf_create_campaign and growsurf_update_campaign_design.

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?

It gives explicit mode-selection guidance ("detail: summary returns a configuration draft and reward structure; detail: full adds detailed benchmark tables") and notes that incentive amounts and qualifying actions remain unresolved unless the customer supplies them. It does not explicitly name alternative sibling tools or state when to prefer this over directly creating a program, so it stops short of a 5.

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