Compare two sets of supplied AI answers

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: it only pairs 'complete' answers, it reports sample counts, and it explicitly does not infer causation or call AI providers — useful scope limits that prevent misuse.

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, front-loaded with the matching precondition and followed by what is returned and what is out of scope. Dense but every clause carries information; no filler.

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?

Returns are summarized (paired mention and citation changes with sample counts), which is needed since there is no output schema. Still missing for a 5-parameter comparison tool: how before/after records are paired (id? normalized prompt?), what happens to unmatched records, and the role of aliases and brandDomain.

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 0%, so the description carries the burden, and it only partially does. It enumerates the matching keys (prompt, source, provider, model, surface, locale, search mode, prompt type) which map to fields inside the before/after items, but brandName, aliases, and brandDomain are never mentioned — an agent must guess how alias expansion or a brand domain affects mention matching.

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 sets of supplied AI answers — and specifies the gating condition (complete answers with matching normalized prompt, source, provider, model, surface, locale, search mode, prompt type). That distinguishes it from siblings like edgeo_analyze_visibility or edgeo_query_model, though it never names those siblings explicitly.

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 gives a validity precondition ('only when ... match'), which implies when a comparison is meaningful and implies that mismatched records are excluded. It does not state when to prefer this over edgeo_analyze_visibility or edgeo_query_model, nor what happens if no pairs match (error vs empty result).

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