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

With readOnlyHint=false and no output schema, the description carries the burden well: it explains why the call is not read-only ('Uses one read and saves the result in the user's Puley history'), discloses the batch cap, lists the upstream sources consulted (Open Library, Deezer, JustWatch, OpenAlex, Wikidata, Google Maps, Amazon US), and enumerates the possible verdicts (Real, Different details, Misattributed/Disputed, Closed, Not found, Couldn't confirm). That is substantive behavior beyond the annotations, consistent with openWorldHint=true.

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 verdict list are front-loaded in the first sentence, with sources and cost shoved to the back, which is the right ordering. The middle sentence is dense – a long comma-separated source roster – but each element is informative for trust assessment rather than filler.

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 moderate-complexity, open-world lookup tool with no output schema, the description covers what to send (kinds, cap), what comes back (six verdict types plus link/details), and what it costs. It does not say how partial or per-item failures appear when only some of the 15 items resolve, which is the main remaining 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?

The top-level `things` array is undocumented in the description beyond the '15' cap, and the reported schema coverage is 0% (though the nested Thing properties do carry their own field descriptions). The description adds the batch constraint and clarifies that quotes are checked as words and people come back with description/dates, which is useful but limited relative to the ten-value `kind` enum and the `by`/`year`/`place` disambiguators.

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 opens with a specific verb + resource: 'Check whether the books, songs, albums, films, shows, papers or citations, people, quotes, places or products named in an answer really exist.' It enumerates the exact entity kinds it handles, which matches the `kind` enum in the schema, so an agent can distinguish it from look-alike siblings such as check_links, google_results, or find_news 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?

It implies the trigger context strongly ('named in an answer' – i.e. fact-checking a draft or response) and gives a hard operating limit ('Up to 15') plus a cost note ('Uses one read'). It does not explicitly name an alternative tool or state when NOT to use it, so it falls short of a 5, but the usage context is unambiguous.

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