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

Annotations already cover read-only, idempotent, closed-world, non-destructive, so the description is free to add real behavior: at most three results, best-first ordering, match score 0-100 with a reason, the answered=false sentinel, and the deterministic matching order (exact phrase, exact pair, named entity, then word overlap). What it omits is threshold definition and what happens when both path and query are supplied.

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 core purpose and the answered=false fallback are stated up front, but the middle is a 16-item enumeration of page types that no agent can hold in working memory and that the examples already convey. It is dense and every sentence is roughly on-topic, yet the list is longer than it earns.

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 does the heavy lifting by describing the card payload (title, address, dated lead sentence, JSON-twin numbers, score, reason). The remaining gap is numeric specifics: what the threshold is and whether fewer than three results can be returned without answered=false.

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, but the description adds interpretive value by explaining that query is free-form reader language whose matching is deterministic and ordered, and that path is an alternate selector for one page's card rather than an additional filter.

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 and resource — find the ETFIQ page that answers a question — and enumerates the page kinds it covers, plus the card contents. An agent can distinguish this from etf_search, etfiq_page, or etf_rankings without opening any schema.

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?

Gives explicit when-to-use criteria ('any question one ETFIQ page answers') with four concrete example questions, plus a when-not path: 'answered is false when no page reaches the threshold: then answer with the other tools.' It also names the path-vs-query alternative for reading a single known page.

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