caselaw_list_sources

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. Being a metadata/provenance tool, it's reasonably likely to be non-destructive and read-only, which is implied by 'Provenance and legal-basis metadata.' However, it does not disclose the return format, whether it performs network requests, authentication needs, or data freshness characteristics. The description gives enough to infer a safe, informative call but doesn't add depth beyond the obvious metadata purpose.

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 sentences deliver both purpose and usage guidance with zero wasted words. The 'Call FIRST' instruction is front-loaded and actionable. This is exemplary conciseness—every word earns its place.

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 zero-parameter metadata/discovery tool with no output schema, the description is appropriately complete. It establishes the tool's role (provenance and legal-basis), identifies the source (SAOS), and prescribes when to call it (FIRST). It could optionally hint at what downstream decisions this metadata informs, but given the tool's simplicity and the lack of output schema, this is sufficient. The main gap is that it doesn't describe what the returned metadata looks like, but no output schema exists to supplement this.

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?

The tool has zero parameters, and the description provides contextual semantic value beyond the empty schema. It tells the agent what metadata categories are returned (provenance, legal-basis, SAOS coverage), which would not be inferable from the schema alone. With 0 params, the baseline is 4, and since the description meaningfully adds conceptual context about the tool's informational scope, it earns that baseline.

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 this tool provides provenance and legal-basis metadata for the case-law source (SAOS), using a specific noun (provenance/legal-basis) plus resource (case-law source). It indicates this is a metadata/provenance tool rather than a search or retrieval tool, which helps distinguish it from siblings like search_case_law and get_judgment. However, the purpose lacks a verb—it describes what it contains rather than what action it performs, and differentiates only weakly from the similar caselaw_about sibling.

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 explicit usage instruction: 'Call FIRST to understand what this case-law server covers.' This provides clear when-to-use guidance, positioning it as a discovery/prerequisite step before other tools like search_case_law or get_judgment. It does not explicitly state when NOT to use it or name alternatives, so it misses the full guidance credit, but the 'Call FIRST' directive is strong actionable context.

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