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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered externally. The description adds only the 1–3999 bound and the 'canonical' constraint (implying non-canonical input like 'IIII' is rejected), which is light value for a pure-function tool; error behavior for invalid input is not stated.

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?

One sentence, imperative and front-loaded, covering both directions with zero filler. Every clause (range, canonical form, reverse direction) carries information.

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 two-parameter pure conversion with a full output schema and complete annotations, the description covers what an agent needs to select and call it. It could be slightly more explicit about failure behavior at the domain edges (0, 4000, non-canonical numerals), but nothing essential is missing.

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 baseline 3 applies: the value parameter's type, length bounds, accepted cases, and the direction enum are all documented in the schema. The description's only addition beyond the schema is the word 'canonical', which marginally narrows accepted Roman input.

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+resource ('Convert whole numbers to Roman numerals' and the inverse), including the exact domain 1–3999 and the 'canonical' qualifier. An agent can distinguish this from neighbors like base_convert, decimal_to_fraction, or epoch_convert without inspecting any schema.

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 bidirectional phrasing makes the two operating modes clear, and the direction enum plus example reinforce it. It stops short of explicit routing guidance (e.g., what to do with out-of-range numbers or non-canonical numerals), so it is clear context without exclusions.

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