get_corrections

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

Annotations already establish the tool as readable and non-destructive, and the description adds concrete behavioral detail: the returned fields list and caps, plus limit-based and since_year filtering. It doesn't cover pagination or explicit max behavior beyond the limit cap, but that's appropriate for a simple read-only tool.

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 compact and front-loaded: action, return value, use case, then parameter guidance. The empirical Title 48 correction count earns its place by making the since_year advice concrete and actionable.

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 and the tool is read-only, the description covers return contents, usage context, and the two configurable parameters meaningfully. Title_number is implicit, but adding a direct one-line explanation would make the already self-contained description fully explicit.

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?

With 0% schema description coverage, the description carries the semantic weight. It explains limit's default and max and since_year's filtering behavior, and while title_number is not mentioned by name, the opening line's 'CFR title' makes its meaning clear enough.

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 'Get editorial corrections for a CFR title,' identifying a specific verb, resource, and scope. The description explains it returns a list of corrections and frames its use case around checking whether a section's text has been corrected, distinguishing it from sibling tools like get_version_history or find_recent_changes.

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 gives a clear use case: checking whether a section's current text has been corrected since its last amendment, and recommends using such to focus recent corrections. It does not mention explicit alternatives or when not to use the tool, so it stops short of full guidance.

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