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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond annotations: it explicitly denies fetching and causality claims, notes 'stable' counts, and mentions the $0.05/call fee. This is useful extra context within the lower bar set by 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?

The description is two compact sentences plus a pricing tag. It leads with the main verb and key object, specifies outputs, and adds a caveat ('without fetching or making causality claims') without redundancy. Every clause adds value.

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?

There is no output schema, so the description must convey return values; it does by listing counts, pair counts, support, Jaccard overlap, and digests. It also states input constraints via 'bounded observation groups' and explicitly disclaims fetching/causality. 'Digests' is not fully explained, but the tool is a simple analyzer with clear scope, so a 4 is fair.

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 already documents both parameters (groups and schemaVersion) thoroughly. The description mostly restates the conceptual purpose (opaque signal IDs, bounded groups) and does not add new parameter-level syntax or format 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 opens with a specific verb ('Measure') and clearly specifies the resource ('buyer-supplied opaque signal IDs appear together in bounded observation groups'). It enumerates concrete outputs (stable signal counts, unordered pair counts, support, Jaccard overlap, digests), which distinguishes it from sibling tools like the cross-tabulator or metrics aggregator by focusing on co-occurrence statistics.

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 provides clear context by stating it works on bounded observation groups and explicitly excludes fetching or making causality claims. This signals when not to use it (e.g., when causality or external data is needed), though it does not name specific alternative tools. That is clear context with implicit exclusions, scoring a 4.

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