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

The description goes well beyond the readOnly/idempotent annotations by disclosing exact edge-case behavior: not_found with parsed, refusal on ambiguity, no near-match suggestions, handbook sections resolving to their own register, related documents kept separate, and identical copies surfaced in also_at. This is rich, non-obvious behavioral detail that an agent needs to interpret results correctly.

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 longer than average, but nearly every sentence covers a distinct behavioral nuance needed for correct use. The core purpose and examples are front-loaded, and the edge cases are grouped logically, though the examples list is somewhat long and could be trimmed without losing the core message.

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 a single parameter, no output schema, and meaningful edge-case complexity, the description covers the essential outcomes: resolved register, not_found with parsed, ambiguous error, related documents, and also_at copies. It does not fully describe the shape of a successful register result, but it provides enough guidance for an agent to invoke the tool and handle the documented error cases.

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 and only the word 'citation' in the schema, the description carries the full burden. It compensates with a wide variety of concrete citation formats ('4000.1 II.A.8.d', '38 U.S.C. 3737', 'SOP 50 10 8 B.Ch1.A.2'), giving the agent a strong sense of acceptable input shape beyond 'string'.

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 states a specific action — 'Resolve a regulatory citation ... to a register' — with a rich set of concrete examples that make the tool's scope unmistakable. It also clarifies what the tool is not (it refuses ambiguity and does not suggest near matches), which differentiates it from search-like siblings such as search_regs.

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 behavioral context — when a citation parses but is missing, when it is ambiguous, and how to respond to an 'ambiguous' error — but it never explicitly names sibling tools or states when to prefer lookup_citation over search_regs, get_reg, or find_in_section. The guidance is implied rather than stated as direct selection criteria.

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