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

With no annotations provided, the description carries the full behavioral burden, and it does so thoroughly: it discloses statelessness, content-addressed determinism, the possible result leaf states (WIN, CODE_IR_DIVERGED, NOT_KNOWN, REFUSED_*), and the exact comparison criterion. It even tells the reviewer that re-checking is done by re-digesting rather than re-reading a diff.

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 dense and front-loaded: within the first sentence an agent knows what the tool compares and what payload to send. Each later sentence adds a distinct decision-relevant detail—outcomes, determinism, and scope limitation—without padding or significant repetition.

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 tool with no output schema, no annotations, and nested-object inputs, the description covers the input contract, all result signs, determinism, and equivalence semantics. The legacy left_ir/right_ir fields are covered by the schema, and the description is complete enough for an agent to call this tool without further inference.

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 baseline is 3. The description adds value by explaining the payload model: two whole source files can be supplied as left_file/right_file or as a two-element files array, and the result echoes those same files. This links the parameter mechanics to the output structure in a way the field descriptions do not.

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 precise verb and resource: it decides whether two implementations are equivalent by comparing the exact value multiset of their LLVM IR constants. It also explicitly distinguishes itself from full behavioural equivalence, which separates it from the many verification-style siblings in the tool list.

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 positions the tool as 'The Code Court's first move' and as a 'necessary, strong condition for the numeric kernels,' giving clear context for when it applies. It explicitly says it is not full behavioural equivalence, but it does not name a specific sibling tool as the alternative for that broader comparison.

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