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

Annotations already mark it read-only/idempotent/non-destructive, and the description adds real substance on top: the 25-result cap, ranking order, dual matching strategy (case-insensitive substring on display name OR shortname, plus trigram similarity so typos resolve), the concrete `asault` → Assault Rifle example, 5-minute caching per query, and the exact result shape. This is well beyond what the annotations provide.

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?

Purpose and cap are front-loaded, then matching semantics, then the escape hatch to other endpoints. Nearly every clause earns its place; the 'same ILIKE + similarity search the site's item pickers use' aside is minor color that could be trimmed, and the prose is dense in a single block.

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 compensates by spelling out the result object fields `{shortname, display_name, category, icon_url}` and the cap on result count. Combined with the caching note and the follow-up call path, an agent has everything needed to invoke it and use the response correctly.

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% and documents the single `q` parameter, so the baseline is 3. The description goes further by explaining what `q` actually matches against — display name OR shortname, substring plus fuzzy trigram similarity — which the schema does not state and which materially shapes good query construction.

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 (typeahead search) and resource (item display name / shortname) and immediately bounds the result set to 25. It is clearly separable from get_item (fetch one by shortname), browse_items (browse), and search_skins (a different resource).

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?

Explicitly routes the agent: this tool for live typeahead, `/items?search=` for filtered/paginated results, and `/items/{shortname}` for follow-up. The alternative referenced is a REST route rather than a named sibling tool (e.g. browse_items), so the in-tool routing is slightly less crisp than it could be, but the when-to-use condition is clear.

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