colab_session_create

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

With no annotations, the description carries the full burden, and it does add real value by disclosing the failure modes (SESSION_ALREADY_EXISTS, QUOTA_EXCEEDED, AUTH_EXPIRED, CLI_ERROR) and the Pro/Pro+ gate on high_mem. However it omits key behavioral facts: what hardware is provisioned by default, whether gpu and tpu can be combined, and what the cost/lifetime implications of a created session are.

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?

The docstring layout is front-loaded with the action verb first, then Args/Returns/Raises, and every line carries usable information. The Returns block is mildly redundant given an output schema exists, but the structure is efficient overall.

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 4-parameter creation tool with no annotations, the description covers parameters, return shape, and error cases — enough to call it correctly. Missing the default hardware profile and gpu/tpu compatibility keeps it short of complete, though the existing output schema reduces the need to explain return values in detail.

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 description coverage is 0%, so the description must compensate — and it does, enumerating the concrete accepted values (gpu: T4, L4, G4, H100, A100; tpu: v5e1, v6e1) that the bare schema lacks entirely, plus explaining that name is auto-generated if omitted. The remaining gap is that gpu/tpu interaction (mutual exclusivity vs. both allowed) is never stated.

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 and resource ('Create a new Colab session') that an agent can immediately distinguish from siblings like colab_session_list, colab_session_get, and colab_session_stop. It does not explicitly name a sibling or contrast with alternatives, but the create/get/list/stop family is unambiguous from the name and the verb.

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?

Usage is only implied: an agent infers it must create a session before colab_code_execute or colab_session_get_url can work. The only explicit guidance is the prerequisite note that high_mem 'requires Pro/Pro+'. Nothing states whether gpu and tpu are mutually exclusive or what the default hardware is if neither is supplied.

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