get_reference_sources

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond that: it describes the payload as an 'index' with citation scope, limits and dataset versions, and explicitly states it does not fetch linked pages, which prevents the agent from expecting per-URL content.

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, front-loaded with the resource and its contents, with the clarifying limitation placed last. No filler or restated metadata to trim.

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?

With no output schema and no parameters, the description must carry the return-value burden, and it does — it enumerates the index contents (links, languages, citation scope, limits, versions) and rules out page fetching. Nothing an agent needs to invoke it correctly 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?

The tool takes zero parameters, so the baseline of 4 applies. The description is consistent with a no-argument tool and gives no misleading hints about inputs.

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 uses a specific verb ('Read') and resource ('the current public reference index') and then enumerates its contents: source links, languages, citation scope, limits, dataset versions. This is far from a tautology and clearly distinguishes it from the sibling tools (catalog, article, stick), though it never explicitly names those alternatives.

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?

There is no explicit statement of when to prefer this tool over the siblings, so usage is only implied. The closing sentence 'It does not fetch each linked page' does provide a useful negative boundary — the agent learns this returns an index, not page content — which lifts it above pure absence of guidance.

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