list_sources

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that all live datasets are included and that they are 'public', which hints at access permissions. However, it fails to mention pagination, ordering, potential response size, or any rate limits or latency implications, which are important for a tool that returns an entire catalog.

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?

The description is a single, information-dense sentence that front-loads the core concept ('Dataset catalog + freshness') and then lists the specific fields returned. There is no fluff. However, the typo 'Clous' and the abbreviated phrase 'catalog + freshness' slightly reduce clarity, preventing a perfect score.

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 low-complexity tool with no parameters and no output schema, the description covers the essential return elements (endpoint, record count, last sync). It gives a clear picture of what the tool provides, but it does not explain issues like pagination or how it fits with sibling tools. Given the simplicity, the description is largely sufficient but leaves a few gaps.

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?

There are zero parameters, so the input schema is empty. The description appropriately focuses on what the output will contain (endpoint, record count, last sync), which helps set expectations for the return payload. With no parameters, the baseline is 4, and the description aligns well by explaining the result semantics.

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 identifies the tool as a dataset catalog that lists every live Clous dataset with its endpoint, record count, and last sync. It distinguishes from sibling search tools by emphasizing the broad catalog scope. However, it uses the noun phrase 'Dataset catalog' rather than an explicit verb like 'list' or 'retrieve', making the purpose slightly less direct than ideal.

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?

Usage context is implied: this tool is meant for discovering available datasets. But there is no explicit guidance on when to use it versus alternatives like search_filings or get_company_financials. No exclusions, prerequisites, or alternative tool references are given, so guidance is weaker than a clear when-to-use statement.

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