Score ad

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'prediction' framing is fully consistent with that safety profile. The description adds useful behavioral context beyond annotations by revealing the analytical nature of the output — per-dimension scores and a single recommended fix — setting agent expectations that this is an analysis, not a mutation. No contradiction with annotations.

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 sentences with zero filler. The main purpose and output breakdown are front-loaded in the first sentence, and the usage directive occupies the second. Every clause 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?

The tool has no output schema, so the description compensates by summarizing what is returned (score, dimension breakdown, strengths, fix). Combined with simple fully-documented params and annotations covering the safety profile, the agent has enough to invoke it correctly. Minor omissions — score scale, response format, or video processing latency — prevent a 5.

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 100%, so the schema fully documents url, kind, and intent. The description adds marginal linkage value by tying 'goal fit' to the intent parameter and 'image or video URL' to the kind enum, but it does not add format or syntax details beyond the schema. Baseline 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 states a specific verb-resource pair: 'Virality/performance prediction for a finished ad (image or video URL)' — clearly an evaluation tool, not a creation tool. It enumerates the exact output shape (overall score, per-dimension breakdown, strengths, biggest fix) and distinguishes itself from siblings like plan_ad, render_ad, make_template_ad, and check_ad_policy by scoping to 'finished' ads.

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 explicit when-to-use guidance: 'Use BEFORE spending on distribution, or to rank variants.' This gives the agent a clear decision rule. It does not name alternative tools or give when-not-to-use exclusions, 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.