keep_run_workflow

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

Annotations already declare readOnly=false, idempotent=false, destructive=false, openWorld=true; the description adds the non-obvious facts that every run creates a new execution, that dry-run is the default without confirm, and that Keep backfills missing alert status/severity/name/id. It does not cover failure modes such as an unknown workflow_id or what the run response contains.

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 purpose is front-loaded in four words, and the remaining sentences are short and declarative, each carrying a distinct fact. A few lines, such as the literal POST path and the repeated default statements, duplicate structured data and could be trimmed.

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 7-parameter, open-world mutation tool with a nested body object and no output schema, the description covers defaults, replay, dry-run safety, and execution creation well enough to invoke it correctly. Permission requirements and return/response behavior are the main omissions, and neither is fully required here.

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 86%, so the schema already documents most fields; the description still adds cross-parameter meaning, notably that type defaults to alert, that body fields are interpreted as alert vs incident (status/severity defaults differ), and that event_type and event_id work as a pair. That is meaningful semantics beyond the schema nodes.

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 description opens with a specific verb+resource ('Run a workflow') and pins down the exact endpoint and payload shape (POST /workflows/{workflow_id}/run with type, body, inputs). It is clearly separable from keep_list_workflows, but it never explicitly names a sibling, so the differentiation is implicit.

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 gives concrete conditional guidance: omit confirm for a dry-run preview, use event_type with event_id to replay a stored alert, and it explicitly rules out incident replay as unimplemented. It stops short of saying when to prefer this over alternatives such as acknowledging or resolving an alert directly.

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