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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It reveals that the tool will refuse to answer rather than estimate, and it explains the underlying data source (ETFIQ's comparison page). This is meaningful behavioral context an agent could not infer from the schema alone.

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?

The definition is compact and front-loaded: the first sentence states the core result, the second gives the use case, and the third defines the refusal boundary. Every sentence earns its place, and there is no redundant or promotional language.

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?

For a simple two-string-parameter tool with no output schema, the description covers what the tool does, when to use it, and when it will decline to answer. The remaining gap is parameter format and the exact output representation, but the refusal behavior addresses the most likely source of agent error.

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?

The schema has two unnamed string parameters with 0% description coverage, so the description needed to compensate. While 'two funds' and 'the pair' hint that a and b correspond to funds, the description never explains whether these should be tickers, ETFIQ IDs, names, or some other identifier, and it doesn't state that the tool is symmetric in parameter order.

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?

The description clearly identifies the tool's function: reporting how much of their weight two funds hold in common, as published on ETFIQ's comparison page. It also gives concrete triggering questions ('whether two ETFs are the same thing, or whether owning both adds anything') that separate this pairwise tool from single-fund siblings like etf_holdings or etf_profile.

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?

The description explicitly states when to use the tool—for overlap or redundancy questions between two ETFs—and clearly describes a when-not condition: it refuses rather than estimating when the pair is not compared or holdings data is incomplete. It does not name sibling tools as alternatives, but the usage context is strong enough to guide selection.

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