Reset gitlab runner token

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

Annotations already cover safety flags (non-read-only, non-destructive, non-idempotent, open-world). The description adds genuine value by disclosing the return payload ('raw token data'), which matters since the point of a reset is retrieving the new token. It omits the key side effect: what happens to runners or jobs registered with the old token, which is the main risk an agent should weigh.

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?

Very short and front-loaded, with the purpose in the first sentence. The 'Returns:'/'Raises:' blocks are template boilerplate but each carries one useful fact, so there is little waste.

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, describing the response shape is necessary and done adequately. However, for a mutation that invalidates a registration token, the definition never states the consequence of the reset or how it differs from the other reset-token siblings, leaving a meaningful gap.

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?

Zero parameters, so the baseline is 4. The 'Raises: ParameterError' line is a bit incongruous for a no-argument tool but does no harm.

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?

It names a specific verb and resource ('Reset GitLab runner registration token'), but the scope 'gitlab runner' is ambiguous when three siblings exist (gitlab_reset_group_runner_token, gitlab_reset_project_runner_token, gitlab_reset_token). Nothing in the text tells an agent this is the instance-level variant rather than a group/project-scoped or generic token reset.

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?

No when-to-use guidance at all, and the sibling set contains near-identical reset-token tools that an agent must discriminate between. The description offers no conditions, prerequisites, or alternatives.

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