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

Annotations only declare readOnlyHint, so the description carries the rest and does add real value: ranking semantics, the point that word spread is a label and never a penalty, the ESCO-read-through-crosswalk constraint, and the fact that every call returns a ten-stage step-by-step report even on a miss. That last detail is unusually useful for interpreting empty results. It stops short of describing error conditions or output size.

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 leading question front-loads the purpose effectively, but the rest is a single run-on sentence with a long, heavily parenthesized enumeration of identifier types. That list is necessary information, yet the packing makes it hard to parse and crowds out the return-behavior details.

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 takes on the burden of explaining returns, and it does say what comes back: ranked words with spread labels plus the ten-stage report and official links. The remaining gap is that 'spread' is used as jargon without definition, and the ranked list's shape is only loosely characterized.

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 coverage is 100%, so the single 'code' parameter is already documented, giving a baseline of 3. The description does expand the accepted identifier set beyond the schema (O*NET Technology Skills categories, UNSPSC commodity codes, Detailed Work Activity ids, ESCO occupation/skill URIs), which is helpful, but it adds no format or syntax guidance for constructing a value. Given the full schema coverage, the net gain is modest, so it does not rise above the baseline.

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?

Opens with a specific framing question ("Which words reach this code?") and then states a concrete verb+resource: answers the words that reach a given code, ranked by catalog usage. The accepted identifier space is enumerated, so an agent knows what it can pass in. It does not, however, distinguish this from siblings like crosswalk_code, which likely takes similar identifiers.

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 'Given X, answers Y' construction implies when to reach for it, and the ESCO clause implicitly directs code-to-code mapping elsewhere. But there is no explicit when-to-use vs. when-not, no named alternative such as crosswalk_code, and no stated prerequisites for the caller.

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