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

Annotations already declare this read-only, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: AND-matching across all query words, a hard cap of 50 records per call, and the fact that each hit carries a source URL and an Eyes on Flash cite. It still omits ordering, behavior on zero matches, and whether paging is stable.

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, front-loaded with the search semantics and backed by two illustrative queries that do real work in showing term composition. Nothing is redundant with the name or title, and the return-shape note is appended rather than buried.

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 correctly compensates by stating what each result contains (source URL plus cite) and the per-call ceiling. The presence of limit/offset paging and an enum-restricted dataset filter is handled by a fully documented schema. Minor gaps remain around result ordering and empty-result behavior for a tool an agent will likely page through.

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 the baseline is 3, but the description adds real meaning the schema lacks: the bare "Words to match" becomes an explicit conjunctive requirement ("words that must all appear in a record") and the kind of vocabulary that works is spelled out with examples. The 50-record ceiling is echoed consistently with the schema maximum, though offset and dataset semantics are left entirely to the schema.

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 sourced figures by words") and enumerates the matchable fields (maker, part, measure, company, quarter, site) with two concrete example queries, so the agent knows exactly what kind of lookup this is. It does not explicitly contrast itself with the sibling get_record (single-record fetch by id) or list_datasets, leaving that distinction to inference.

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 description conveys the key matching rule — every word must appear in the record — which implicitly tells the agent this is a narrowing keyword search rather than a fuzzy one. However, it never says when to prefer this over get_record or list_datasets, nor when results would be empty or how to refine. Usage is implied rather than guided.

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