create_datasource

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

Annotations: readOnlyHint=false, destructiveHint=false, idempotentHint=false. Description adds write permission requirement and notes format compatibility but doesn't elaborate on side effects beyond overwrite parameter. The destructiveHint=false may be contradicted by the overwrite parameter which deletes, but description doesn't explicitly claim no destruction.

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?

Four sentences, each with a distinct purpose: what it does, permission, format, usage scenarios, and special case. Front-loaded with verb+resource.

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 creation tool with one required object param, it's fairly complete. Notes permission, format compatibility, alternative uses, and special type values. Lacks output/return info but no output schema exists.

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 covers both parameters (overwrite, definition) at 100%. Description adds meaning by explaining definition must be REST API format and that overwrite deletes existing. The Script datasource type values note adds extra param-related guidance.

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?

Clear verb (Create) + resource (DataSource) + method (REST API from full definition dict). Distinguishes from import_datasource by format (REST API vs LM Exchange). Mentions round-tripping with export_datasource.

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?

Explicitly says use for round-tripping exports or building from scratch, and directs to import_datasource for LM Exchange format. Also notes Script DataSource datapoints require appropriate type values.

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