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

Annotations already establish readOnlyHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds meaningful context beyond that: which fields come back (type, host, database, last test status, shared/owned), that sharing is read-only, and the security-relevant promise that 'Passwords are never returned'.

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 and scope are front-loaded in the first sentence, and each subsequent sentence addresses a distinct field or downstream consequence. The single dense paragraph is information-rich but heavy; splitting the field glossary from the routing advice would improve scanability without losing content.

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 parameters and no output schema, the description carries the full burden of explaining return values, and it does so for every notable field plus the security caveat. An agent has enough to decide whether a returned source can be queried live, materialized, or shared in a dashboard.

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 input parameters, so the baseline is 4 and no schema compensation is needed. The discussion of `dataSetOnly`, `publishable`, `hasNotes`, and `sourceSelection` describes returned fields rather than inputs, which is valuable but could momentarily be mistaken for parameter semantics given the backtick notation.

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 opens with a concrete verb and resource: 'List the Data Sources you can use — both your own and any shared with you', and enumerates the connector types covered. This distinguishes it from postgres_query/postgres_schema, but it never clarifies its relationship to sibling listing tools like github_list_connections or spreadsheet_list, even though its scope ('every connector type') appears to overlap them.

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 gives explicit routing guidance for the sources it returns: SaaS sources marked `dataSetOnly: true` 'cannot be queried live or browsed with postgres_query/postgres_schema, only materialized with dataset_create', and owners' notes should be read via postgres_schema 'before querying'. What's missing is guidance on when to call this list tool at all versus the other connection-listing siblings.

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