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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add return behavior — and it does, stating the result carries layer, region and unit but 'no prices'. That negative disclosure is genuinely useful for an agent deciding where to get pricing data. Rate limits, result caps and ordering are not mentioned.

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 tightly packed sentences: capability first, then return shape and exclusions. Every clause earns its place — the examples, the layer legend and the 'no prices' caveat all carry information an agent needs.

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 usefully describes what comes back (code + layer, region, unit) and what does not (prices). Combined with annotations this is nearly sufficient; only the result-count/limit behavior is left unexplained for a search tool that caps at 25 results.

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 only 33%, so the description must compensate. It does for 'query' by giving literal example search terms and for 'layer' by translating L0–L3 into plain language, though layer semantics are already in the schema. The 'limit' parameter (default 10, max 25) is never addressed, leaving a gap the description should have closed.

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 PackIndex codes') and enumerates the searchable dimensions (material, input, format, plain words) with concrete example queries. An agent can tell this apart from lookup-style siblings like packindex_query without opening a 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?

'Use first when you don't know the exact code' gives a clear selection condition and implicitly positions this ahead of exact-code lookup tools. It stops short of naming the alternative tool to use once the code is known, so the routing is only half explicit.

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