Erase project job

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

The description uses the destructive verb 'erase', yet annotations declare destructiveHint=false (and non-readOnly, non-idempotent). That conflict is exactly the kind of signal the agent relies on to decide whether a call is safe. Beyond the verb, nothing is disclosed about irreversibility, required permissions, or which artifacts are discarded.

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 lead sentence is front-loaded and clear, but the Args/Returns/Raises docstring boilerplate adds little; the kwargs line is vague and the Returns block restates routine wrapper behavior. Roughly half the text does not help an agent decide how to call the tool.

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 mutation tool with no output schema and 11 undocumented parameters, the description should carry far more weight: what erasure removes, whether it can be undone, and what response to expect. The mention of a Job model wrapper and MissingParameterError/ParameterError raises is minimal boilerplate rather than task-relevant context.

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% across 11 parameters, and the description only gestures at 'project_id, job_id' inside a generic kwargs wrapper. The puzzling pagination/filter leftovers (page, per_page, max_pages, total_pages, scope, include_retried, job_variable_attributes) go entirely unexplained, so the agent cannot tell which are meaningful for a single-job erase or which are ignored.

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?

"Erase a specific job within a project" gives a verb and resource, but 'erase' is GitLab jargon whose actual effect (permanent removal of the job's log and artifacts) is never stated. It also does not distinguish this from nearby siblings such as gitlab_cancel_project_job, gitlab_retry_project_job, or gitlab_get_project_job_log, leaving the agent to guess what is being removed.

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?

There is no guidance on when to use this versus cancel/retry/delete-job siblings, and no mention of prerequisites (maintainer/owner role, job must be finished, erasure is irreversible). The agent gets no context or exclusion rules.

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