Check compatibility of two exact versions

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

With no annotations, the description carries the full burden of disclosing behavioral traits. It reveals that argument order carries meaning, that relation.direction reports server interpretation, and that an 'unknown' verdict is normal, not an error, with limitations and sources_checked pointing to next steps. This fully compensates for missing 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 dense with necessary information, but it is somewhat long. However, every sentence contributes unique value—scope boundaries, order rules, unknown verdict behavior—and the structure flows logically from purpose to usage to edge cases. Slight over-length is justified by complexity.

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 description covers all key aspects: what the tool does, when to call it, exclusions, argument-order semantics, runtime special cases, and interpretation of outputs ('unknown' verdict). Given the output schema exists, the description complements it well by explaining how to interpret results and where to find more info.

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?

Although the schema already describes field formats, the description adds critical semantics: argument order is meaningful for pypi→pypi and npm→npm, swapping arguments asks a different question, and runtime cases have symmetric order. This goes beyond the schema's generic field descriptions and explains the domain-specific rules.

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 precise question—'Does one exact release work with another exact release, and on what evidence?'—and specifies the subject types (PyPI/npm packages, Python/Node runtimes). This clearly distinguishes it from the sibling get_compatibility_context, which likely provides broader context rather than a compatibility verdict.

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 explicitly says to call this only after 'both sides are pinned,' and prohibits version ranges or file contents, stating resolving ranges and reading code are out of scope. It also provides nuanced guidance on argument order, explaining when swapping arguments changes the question and when it doesn't—this is actionable usage instruction.

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