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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description goes further by explaining output behavior beyond annotations: flags carry the number, date and threshold line crossed, 'none is advice,' and unpublished numbers are listed per fund rather than silently treated as zero. That last point is a meaningful disclosure an agent could not infer from the schema.

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 content is dense and mostly earns its place, but the prose is cramped and occasionally ungrammatical ('the observations to check before the funds are read one by one', 'a leveraged share'), which forces re-reading. The long metric enumeration is useful but would be far clearer as a structured list, and the opening sentence buries the verb.

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 and a nested object parameter, the description does the work of explaining return contents: per-fund metrics, list-level aggregates, flag anatomy, and missing-data handling. An agent could invoke this correctly and interpret the response from the description alone; only edge cases (invalid tickers, weights referencing unlisted tickers) are unaddressed.

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%, so both parameters are already documented, giving a baseline of 3. The description adds some value by giving a concrete weights example with percent units ('{"SPY": 60, "QQQ": 40}') and stating that omitting weights yields equal weighting — a behavior the schema does not specify — but it stops short of clarifying validation or behavior for tickers that appear only in weights.

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 names a concrete role and resource: a risk check over 1 to 20 fund tickers that returns per-fund observations (net assets, fee, top-10 weight, NAV premium/discount, spread, liquidity score, leverage) plus list-level aggregates (pairwise overlap, largest fund, issuer/category shares, leveraged share). This is specific enough to distinguish it from siblings like etf_profile or etf_overlap, though it never explicitly contrasts itself with them.

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 observations to check before the funds are read one by one' implies a pre-screening workflow, and 'for 1 to 20 fund tickers' bounds the input. However, there is no explicit when-to-use versus when-to-use-a-sibling guidance (e.g., when to call etf_overlap instead of relying on this tool's overlap output).

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