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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: results are heuristic candidates ranked by frequency, each carrying the first cue of occurrence, and the tool performs no rewriting — warning the agent that output is a suggestion set, not ground truth.

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 short sentences, no filler; the core action and the frequency/first-cue output shape are front-loaded, and the non-destructive caveat closes it.

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?

No output schema exists, but the description sketches the return shape (ranked terms plus first cue). Combined with full schema coverage and rich annotations, an agent has enough to call it correctly; only the exact result envelope is unspecified.

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% and both parameters (jobId, limit with default 50 and max 200) are documented inline, so the baseline is 3. The description adds only the frequency ranking and first-cue payload context, not parameter-level meaning.

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 and resource ('find candidate proper nouns in a job's cues') plus the ordering and payload ('ranked by frequency, with the first cue they appear in'). The closing clause 'Suggestions for a glossary, not corrections' implicitly separates it from lunara_get_glossary and lunara_rewrite, though neither sibling is named explicitly.

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?

'Suggestions for a glossary, not corrections — nothing is rewritten' gives a contextual hint about intent, but there is no explicit statement of when to call this versus lunara_get_glossary (reading an existing glossary) or lunara_rewrite. The agent must infer the routing.

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