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

With only readOnlyHint available, the description carries heavy extra context: text is not verified against primary sources, must not be presented as the author's exact words unless `verbatim` is true, must be credited with the `attribution` line, and results are cached 24h per argument set. This is exactly the kind of non-obvious behavioral constraint annotations cannot express.

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?

Dense but front-loaded: the resource, the verification caveat, and the argument-dependent return shapes all appear in order of decision relevance. No sentence is filler, including the caching note.

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?

No output schema exists, so the description compensates by specifying both return shapes ({facts, count, total_facts} vs {fact, total_facts}) and the 10-item cap. Combined with the attribution and verbatim rules, an agent has everything needed to call it and to report results responsibly.

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 baseline is 3, but the description adds real meaning: `query` results are capped at 10, a bare `category` or no arguments yields a single random pick, and an invalid category is refused with INVALID_PARAMS naming the valid values. It goes beyond the schema rather than restating it.

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/resource pair: retrieving a curated value-investing principle, historical fact or attributed paraphrase from Oxford Ledge's ~2,000-entry corpus. The corpus size, named authors (Buffett, Graham, Munger, Klarman) and pedagogical framing clearly separate it from quantitative siblings like ol_intrinsic_value or ol_glossary_term.

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?

Explicitly describes the two usage modes (query for search, bare category or no arguments for a random pick) and adds a clear scope boundary: 'Pedagogical content only -- never a market signal.' It does not, however, name a specific alternative sibling for when an agent should prefer a different tool.

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