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

No annotations exist, so the description carries the burden. It does disclose a real behavioral trait: unknown names are refused before payment, with accepted names returned. However, it leaves unclear whether this tool itself is paid, what the output structure looks like beyond a list of names, or rate/access behavior.

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?

A single dense run-on sentence packing version metadata, bundle hash, namespaces, counts, entry rule, and refusal convention into one breath. Every element has some value, but the structure is hard to parse and front-loading is weak.

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?

Given zero params and an output schema, the description covers what the tool supplies (names, representation, unit, versioning, provenance rules, refusal behavior). It doesn't restate return shape because an output schema exists, which is appropriate.

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?

Zero parameters, baseline 4. The description notes an unknown name is refused before payment, but since there are no inputs, little more is needed.

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 specifically what the tool returns: argument names accepted by every tool on the server, with representation and unit, plus version, bundle hash, namespaces and counts. It also clarifies that meanings are not here but in lexicon_resolve/lexicon_bulk/lexicon_bundle, distinguishing it from those siblings.

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?

Implied usage: it's a discovery/spec lookup, and the note that meanings live in the paid resolve/bulk/bundle tools implies this is the free naming layer. But there's no explicit 'call this first when...' routing statement or when-not guidance.

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