ap_compare

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine value with 'Returns tradeoffs; higher score is not satisfaction probability', a real interpretation caveat. It does not, however, say what a 'tradeoff' result contains or how the two artifacts are ranked.

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?

Two compact sentences, zero filler, with the comparison scope and the score-interpretation caveat front-loaded. The phrasing is dense to the point of being slightly cryptic, but nothing is wasted.

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?

Three parameters are untyped opaque objects with nested objects allowed, 0% schema coverage and no output schema. The description gives only a hint about audience/target/formulas defaults and never suggests what keys base, candidate or options should contain, leaving an agent unable to construct a valid call with confidence.

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 coverage is 0%, so the description must carry the load. It does communicate that base/candidate are the two artifacts being compared and that audience, target and formulas are held constant 'by default' (implying the options object can override them). It still leaves the shape of both artifact objects and the options object entirely unexplained.

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 and resource: 'Compare two creative artifacts'. It also scopes the comparison ('same audience, target and formulas by default'), which lets an agent distinguish it from siblings like ap_evaluate or ap_sensitivity. It stops short of explicitly naming which sibling to prefer instead.

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?

There is no when-to-use guidance, no prerequisites, and no exclusion or alternative named among the many siblings (ap_evaluate, ap_sensitivity, ap_tune_parameters). The comparison target is inferable from the verb, but nothing tells the agent when this tool is the right choice over the others.

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