citation_sources

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

With no annotations, the description carries the full burden and largely does: it discloses that it follows redirects, runs read-only via the action API (GET only), and needs no new dependencies. It also explains the aggregation semantics (registrable-domain rollup, citation-count ranking, archived/DOI shares), which is real behavioral context beyond the name. It omits auth expectations and any limits on request size or latency.

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?

Purpose is front-loaded in the first clause, and the detail that follows (grouping rule, shares, sibling pairings) is mostly load-bearing. Some phrasing is slightly padded, e.g. restating the same idea as both 'publishers' and 'sources by domain', but overall it is dense and well ordered.

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?

There is no output schema, so the description must describe the return shape — and it does: a publisher map keyed by domain with citation counts and share, plus archived and DOI shares. Together with the read-only note and sibling pointers, an agent has enough to call it correctly; only auth/limit-of-response details are 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 description coverage is 100%, so the schema already documents `lang`, `limit`, and `title`; baseline 3 applies. The description adds only marginal semantics — it clarifies that ranking is by citation count, which implicitly explains what `limit` cuts off — but adds nothing about the enum or title handling.

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?

It states a specific verb and resource up front — 'Which publishers an article's evidence comes from — its sources by domain' — and then specifies exactly how the aggregation works (off-wiki links grouped by registrable domain, ranked by citation count). It is clearly distinguishable from siblings like `references` (full bibliography) and `external_links`.

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?

It names the audit use case ('the diversity lens for the "can I rely on this article?" audit') and explicitly pairs itself with `references`, `article_quality`, `article_flags`, and `citation_needed`, which routes the agent well. It stops short of explicit when-not-to-use guidance or stating what `references` gives that this does not beyond the parenthetical.

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