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

Annotations only indicate non-read-only and non-destructive behavior. The description adds meaningful behavioral context: re-using an existing name updates that connection's credentials, the first call returns the field list, and unsupported datasources 'say so'. This goes beyond the annotations without contradicting them.

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?

Five sentences carry the full workflow: purpose, first call, second call, upsert caveat, unsupported datasources, and follow-up tools. There is no filler, and the most useful guidance appears early.

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?

Given the output schema exists, rich schema descriptions, and annotations, the description completes the picture: it explains the two-step interaction, the credential-only scope, the reuse/update behavior, and downstream tools to call. An agent has everything needed to invoke this correctly.

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 coverage is 100%, so parameters are already documented. The description adds important semantics: datasource_id alone triggers a field-discovery response, credentials are provided in the format the tool lists, and name is needed on the second call. This enriches the structured schema meaningfully.

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 states a specific verb and resource: 'Create a datasource connection from credentials.' It also differentiates this tool from related siblings by noting that link_datasource and test_connection are used afterwards, and that OAuth-based datasources cannot be created here.

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 when-to-use guidance: call with just datasource_id to discover required fields, then call again with credentials and a name. It also states a clear exclusion — vendor-website OAuth datasources like Google and Meta cannot be created this way — and names the follow-up tools to use.

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