toolbox

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely new behavioral context by disclosing the three-modal structure and the set of sub-tools reachable via call. It does not explain how args are forwarded to the selected sub-tool, nor what discoverability step (describe) is needed before calling. Note a mild tension: readOnlyHint=true while call executes arbitrary sub-tools with free-form args, though the enumerated catalog tools appear read-only so this is not a hard contradiction.

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?

A single front-loaded sentence that leads with the verb and resource, with the twelve sub-tool names packed into one parenthetical that earns its space by telling the agent what the catalog contains. Dense but not padded.

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?

For a dispatcher with a nested free-form args object and no output schema, an agent needs to know the call flow (describe to get a sub-tool's schema, then call with args) and what each action returns. The description names the modes and catalog but omits this workflow, so it is adequate rather than complete.

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 75%, so the schema already documents args, name, and query; only action lacks a schema description. The description compensates partly by binding list/describe/call to finding vs. executing, which clarifies action semantics. It adds no detail on the free-form nested args object, so baseline 3 is appropriate.

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 role: a catalog dispatcher that finds (list/describe) and executes (call) auxiliary tools, and enumerates the twelve categories (legal terms, abbreviations, amendment feeds, article codes, precedents, semantic search, etc.). This makes the meta-tool nature clear. It does not, however, explicitly distinguish itself from primary siblings like statute_find or source_search, leaving the discovery-vs-direct-call relationship implicit.

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 parenthetical mapping of intents to actions (list/describe for finding, call for executing) gives implied usage and the schema confirms the required action enum. But there is no explicit guidance on when to route through toolbox vs. calling a sibling tool directly, and no when-not guidance. Usage is inferable but not spelled out.

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