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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond them: holdings are reference data refreshed only quarterly, which warns the agent the data may be stale, and it discloses the dual single-vs-list response modes.

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?

Front-loaded with the resource and returned fields, then the zero-arg behavior, then the use case and a freshness caveat — a sensible ordering with little waste. The telegraphic field list ("layers.") is slightly terse but not padded.

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 one optional parameter, no output schema, and read-only annotations, the description carries the return-value burden well by naming the fields returned. The quarterly refresh note covers the main risk an agent would face; a note on the ETF universe size or failure mode for an unknown slug is the only visible gap.

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 the single slug parameter's own description already explains the omit-to-list behavior, including an example. The description's "Lists the tracked ETFs when slug is omitted" therefore restates the schema rather than adding format or validation meaning, so baseline 3 applies.

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 resource ("One AI or AI-infrastructure ETF") and enumerates exactly what it returns: issuer, expense ratio, strategy, top holdings with AI Exposure Scores, layers. It also covers the no-argument mode ("Lists the tracked ETFs when slug is omitted"). Differentiation from siblings is only implicit via "Use for fund questions," so it stops short of a 5.

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 for fund questions" gives a broad usage cue, and the omit-slug list behavior is spelled out. There is no explicit when-not guidance and no named alternative (e.g., get_ticker for individual stocks), leaving the agent to infer routing from the ETF-vs-fund framing.

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