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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the tool only returns what the published page contains, the scorecard is conditional ('where one is published'), and missing-page pairs produce an error rather than fabricated data.

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 sentences, but the first is a long comma-spliced enumeration that is hard to parse and front-loads an awkward relative clause instead of the action. The content is dense but the ordering puts page-structure detail ahead of the core operation.

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 carries the return-value burden and does so by listing the page's components, plus it discloses the refusal case and the conditional scorecard. Only the fallback path and parameter ordering are left underspecified, which are minor gaps for a two-param read tool.

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 both parameters carry examples (SCHD, VYM), so the schema does the documentation work. The description adds only that the inputs are a fund pair; it does not say whether a/b order affects the returned title or verdicts, which is the one semantic gap an agent would care about.

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 makes clear this retrieves ETFIQ's published comparison page for a specific pair of funds, and enumerates the page components (title, lead sentence, verdicts, overlap share, FAQ, scorecard). That scope is distinguishable from siblings like etf_profile or etf_overlap, though the opening clause ('Two ETFs compared as ETFIQ's comparison page for the pair publishes them') is grammatically tangled and buries the verb.

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?

There is no explicit statement of when to use this versus etf_overlap (which also covers shared holdings) or etf_profile. The only routing signal is the refusal behavior — 'A pair with no comparison page is refused, with each fund's own page' — which hints at a fallback without naming the sibling tool to call instead.

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