lt_resolve_reference

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

Annotations cover read-only/idempotent/open-world; the description adds genuinely useful behavior beyond them: multiple candidates are returned because numbers aren't unique, and each carries the individual checks (number/date/type/title match, validity on as_of). This tells the agent to expect and interpret a ranked set rather than a single hit. It doesn't discuss ambiguity resolution order or tie-breaking.

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?

Two short paragraphs, front-loaded with the verb and resource, then the rationale and the return behavior. Every sentence carries information; the example citation is the most efficient way to convey format.

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?

An output schema exists and all six params are documented, so the description only needs to explain the intent and candidate/check semantics – which it does. It could go slightly further on how an agent should pick among candidates or what to do when checks conflict, but nothing essential for calling it is missing.

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 coverage is 100% and each parameter already documents its format and examples, so the description can't do much beyond reinforcing the number+date citation pattern. It does clarify that title is used alone when no number is given, a small cross-parameter insight.

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 a specific verb (resolve a citation) and resource (TAR acts), and explicitly contrasts with the identifier-based lookup approach used by siblings like lt_get_act: citations are by number+date, not TAR code. The example citation anchors exactly what input it expects.

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?

Explains the core problem it solves (documents cite by number/date, official numbers aren't unique) which implies when to use it vs. lookup-by-code tools. It doesn't explicitly name a sibling alternative or state exclusions, but the problem framing is a clear selection signal.

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