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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is free. The description adds genuinely new behavior: per-unit cost ($0.001; section=5, document=2), temporal coverage bounds (eCFR history from ~2017, FR search back to 1994), and that each part unit carries its own text. It does not discuss rate limits, failure modes, or what happens when a citation resolves to nothing.

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 capability is front-loaded in the first sentence, and the pricing line is short and useful. The opening nested-quote framing ('One call answers "..."') is slightly marketing-flavored, and the multi-mode enumeration runs long, but no sentence is pure padding.

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 nine-parameter, zero-required, multi-mode read tool with no output schema, the description does the heavy lifting: it sketches what comes back (section plain text, amendment history, underlying final rules) and bounds the cost and history windows. The gap is that with no output schema an agent still cannot anticipate the exact response shape or how an empty result reads, and mode-selection logic remains implicit.

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 description coverage is 100%, so the baseline is 3 and the schema already explains asOf, citation, since, and maxResults thoroughly. The description adds only a little semantic linkage — notably that 'since' is used with a part citation to list what changed — but does not clarify the priority or interaction rules among the nine optional parameters, which is the main ambiguity the schema cannot resolve.

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 names concrete verbs and resources: it returns a CFR section's text as of a date, its amendment history, the Federal Register final rules behind each change, part-level change lists, and FR documents by number or search. Concrete examples ('21 CFR 101.9', '15 CFR 744 this week') make the scope unmistakable and clearly separate it from siblings like eu_law_lookup or national_law_lookup. It stops short of a 5 because the tool bundles four query modes and the description does not crisply frame them as distinct entry points.

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?

Example queries imply which mode to use ('what does 21 CFR 101.9 say today', '15 CFR 744 this week'), and the stated audience of regulatory/compliance agents sets context. However, it never says when to choose this over a sibling such as eu_law_lookup, nor does it explain whether parameters combine (e.g., citation + since + search) or are mutually exclusive; that has to be inferred from the schema.

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