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

Goes well beyond the annotations (which only cover read-only/idempotent/open-world/destructive). It discloses that the call costs 0 credits, that Wex is CC BY-NC-SA, and that the caller must pass on the attribution and licence in the response - an obligation the agent would otherwise miss. It also enumerates the response contents despite there being no output schema.

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, purpose and query examples front-loaded, with cost/licence deferred to the second. The first sentence is long and list-heavy, but every clause (source, explanation, related terms, categories, review date) 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?

With no output schema, the description correctly compensates by enumerating the returned fields, and it covers cost and licensing. It does not say what happens when a term is ambiguous or absent from Wex, which is the only real gap for a one-parameter lookup tool.

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%: the single 'term' parameter already documents format examples and the 'case and spaces do not matter' normalization, and the schema carries its own examples block. The description adds nothing about the parameter beyond restating 'legal term', so the baseline 3 applies.

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 concrete verb+resource+source: 'Definition of a US legal term or doctrine from Cornell LII's Wex legal encyclopedia.' The example questions ('what does habeas corpus mean', 'define adverse possession') make it unmistakable against the retrieval-oriented siblings wex_search and wex_browse.

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?

Usage is clearly scoped by the example query phrasings, which tell the agent this is for single-term 'what does X mean' requests rather than full-text lookup. It stops short of explicitly routing the agent away from wex_search/wex_browse, and there are no stated exclusions.

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