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

The description covers the 'read' nature (no mutation) and explicitly mentions the `source` and `sourceScope` fields reporting which corpus answered the query. But for a read tool with readOnlyHint=true and no destructive field, the bar is lower; the description still doesn't mention potential errors, rate limits, or the impact of date on a search across corpora. It does disclose that search interprets date as text-match day, which is a useful behavioral detail. However, the readOnlyHint annotation already signals safety, so a 3 would be appropriate. I'll settle on 3.

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 description is one comprehensive paragraph covering purpose, modes, parameters, and output. It's front-loaded with the main purpose, but the paragraph is long. It's not overly verbose given the two modes, but it could be more scannable. Still, each sentence adds value, no fluff. I'll give 4.

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?

The description covers the two modes, the parameters that vary between them, the output (snippets, section references), and the sourceScope result field. It mentions the relationship to regulations_get_cfr_section. Given there's no output schema, it explains return values reasonably. Missing: error conditions (e.g., part without title) are only in the schema. Still, quite complete for the tool's complexity.

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 schema covers most parameters (date, mode, title, part, per_page) with descriptions/clarity. The description adds valuable context that the schema lacks — e.g., that query is required in search mode but ignored in structure mode, part can be alphanumeric and matched exactly, and date in structure mode uses historical hierarchy while search matches text on that day. That's meaningful semantic enrichment beyond the schema, worth a 4 rather than baseline 3.

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 clearly states what the tool does: it explores the codified CFR via eCFR in two modes ('structure' to browse the title tree and find a cite, 'search' to run a full-text query). It names the resource (the codified CFR), the two behavioral modes, and explicitly links to the follow-up tool (regulations_get_cfr_section). The purpose is unambiguous and distinguishes the two operations well.

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 explains when to use each mode and how they interrelate — structure mode discovers a cite, search mode queries full text, and a part from structure mode can be fed into search. It stops short of explicitly stating when NOT to use this tool or naming sibling alternatives, so it doesn't hit the top of the scale, but the mode guidance is clear operational direction.

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