co_compare_variants

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by disclosing the comparison scope, the nature of the report (differences and unavailable fields), and the inclusion of decision IDs. It also explicitly lists limitations, which is useful context beyond the 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 no redundancy. The action is front-loaded, and the coverage limitation is stated concisely. Every sentence contributes to understanding what the tool does and what it does not do.

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 read-only comparison tool with no output schema, the description covers the key elements: what is compared, what is reported, and what is excluded. The phrase 'expected document' is slightly ambiguous but understandable in context. It does not mention prerequisites or error conditions, but for a read-only operation with clear annotations, this is acceptable.

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 must compensate. It mentions 'source and candidate variants' and 'same image in the expected document,' giving some context about the relationship between the variant IDs, but it does not explicitly map each parameter (document_id, source_variant_id, candidate_variant_id) to its meaning. The parameter names are self-explanatory, but the description adds no direct semantics for them, leaving a gap.

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 clearly states the action: 'Compare readable settings of source and candidate variants from the same image in the expected document.' It also specifies the output: differences, unavailable fields, and IDs for keeping or reverting. This distinguishes it from sibling tools like co_get_variant or co_list_variants, which retrieve or list but do not compare.

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 clear context on what the tool does and explicitly states what is out of scope ('Mask contents, curves and luma ranges are outside comparison coverage'). However, it does not name any sibling tools or provide explicit when-to-use vs. when-not-to-use guidance beyond its inherent purpose.

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