get_cfr_structure

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context by warning about the 400 error for section-level filtering and clarifies that part/subpart/chapter/appendix accept int or string (matching schema). It also describes the return structure (nested tree with identifiers, descriptions, byte sizes). This goes beyond annotations, though it does not mention potential output size or performance limits.

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 well-organized with a clear opening sentence, a highlighted warning, and a bullet-like list of common patterns. It front-loads the core purpose and adds essential details without redundancy. Though slightly verbose, every sentence contributes value; it earns its length.

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?

Given the output schema exists, the description need not explain return values. It covers the hierarchical levels returned, parameter constraints (int/string), common usage, and the critical limitation. It also handles the optional title_number (default 48) implicitly through examples. For a read-only structure tool, this is complete and fully actionable.

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 0%, so the description must compensate. It explains types for part, subpart, chapter, and appendix ('accept int or string') and provides usage examples, but it omits date, subchapter, and title_number. While the schema already specifies types, the description adds patterns for a subset, leaving other parameters undocumented. This is only partial compensation.

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 the tool's function: returning the hierarchical table of contents for a CFR title or subset. It specifies the resource (CFR titles/chapters/parts/etc.) and distinguishes it from siblings like get_cfr_content (content vs structure) and list_sections_in_part (specific listing vs tree). The verb 'Get' and the explicit scope make purpose unambiguous.

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 provides explicit when-to-use guidance with common patterns (chapter='1' for FAR, chapter='2' for DFARS, part='15', subpart='15.3') and a clear when-not-to-use note: section-level filtering is not supported and returns a 400 error. It advises to use part or subpart then walk children to find sections, which is actionable and prevents misuse.

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