mkt_workflow

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

With no annotations supplied, the description carries the full burden and does deliver the single most important trait: this is read-only, and mutating operations (approve/replay) are explicitly out of scope. It says nothing about return shape, whether list is paginated, or how errors surface for an unknown workflow_id, so the safety profile is covered but operational behavior is not.

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?

A single front-loaded clause establishes read-only scope, followed by a compact mode enumeration and a scope exclusion — no filler at all. The slash-delimited enumeration is slightly compressed and requires the reader to align each item with an enum value, which costs a little structure but not meaning.

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 two-parameter, annotation-free tool with no output schema, the description covers purpose, safety posture, and scope exclusions adequately. It stops short on the workflow_id/action dependency and on what any action actually returns, which an agent would need to call this correctly on the first try.

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 0%, so the description must compensate, and it partially does: the four slash-separated modes (列表/详情/结构校验/运行记录) effectively decode the otherwise bare enum values list/show/lint/status. However, workflow_id is never mentioned — an agent is not told that it is required for show/lint/status but unnecessary for list, which is the main parameter risk here.

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 names a specific resource (workflow) and mode (read-only view), then enumerates four capabilities — list, detail, structure validation, run records — that map onto the action enum. It does not name any of the many overlapping siblings (mkt_plan_lint, mkt_run_queue, mkt_status), so differentiation relies on the reader inferring scope from the 'read-only' framing.

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 one explicit exclusion: approvals and replay belong to the CLI human channel, not this tool. Beyond that, there is no guidance on when to pick mkt_workflow over mkt_plan_lint or mkt_run_queue, which is a real ambiguity given ~40 sibling tools with adjacent names.

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