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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real value on top by enumerating the returned categories and the downstream tool chain, though it says nothing about result ordering, IDs, or shape.

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?

Front-loaded with the verb and the content enumeration, then the workflow, then a doc pointer. Dense with em-dash lists, but every clause carries information an agent needs; nothing is padding.

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, the description compensates by enumerating what the catalog contains and where the result is consumed next. A doc pointer to build_get_skills(doc='connectors') covers deeper detail, leaving the definition sufficient for a read-only listing tool.

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 there is nothing for the description to disambiguate. Baseline applies.

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?

States a specific verb ('List') and resource ('external DATA SOURCE types') and then enumerates exactly what is covered: self-hosted Postgres/MySQL/MSSQL/Oracle/MongoDB, REST APIs, warehouses, and a public-API catalog. An agent can distinguish it from build_list_bound_schemas or connector_plugins purely from this text.

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?

Gives a clear trigger — 'Read this to offer a connect your own data option' — and places the tool in a workflow (build_connect_data_source → build_discover_source → build_bind_data_source). It does not name a sibling to avoid or state when not to call it, so it stops short of full routing guidance.

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