Create DataLens connection

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

Annotations already declare this is a non-read, non-destructive, non-idempotent, open-world write, so the safety baseline is covered. The description adds real value beyond that: credentials are stored server-side and never returned by ``connections_get``, and one connection type is rejected by the API. It omits, however, any warning that repeating the call yields duplicate connections despite idempotentHint=false, and gives no permission requirements.

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?

Three short sentences, front-loaded with the action and return value, then placement, then the security note and the exclusion. The final sentence is a little long, but each sentence carries distinct information with no filler.

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 one-parameter create tool with an externally referenced nested schema and no output schema, the description covers the essentials: return value, placement scope, credential handling, and a known unsupported case. Missing only secondary detail such as required permissions or duplicate-creation behavior.

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% for the single top-level ``connection`` object, so baseline is 3. The description goes further by explaining that ``workbook_id``/``dir_path`` sit inside that payload and that the actual type-specific schema is external and must be fetched with ``schema_get`` for ``ConnectionCreate``, which is meaningful guidance for a nested-unknown object.

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 first sentence states a specific verb and resource ('Create a connection') plus the return value ('return its id'), which no sibling duplicates. The description also implicitly separates it from read/update paths by naming ``connections_get`` as the reader. An agent can identify this as the creation primitive without opening the schema.

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 tells the agent where the resource must live (``workbook_id`` or ``dir_path``) and gives an explicit exclusion plus workaround: gsheets connections cannot be created here and must be made in the UI. It does not name a fallback tool or state prerequisites beyond that, so it stops short of full when/when-not/alternatives coverage.

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