duddy_precheck_plan

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

With no annotations present, the description carries the full burden, and it clearly discloses the most important trait: it is a non-executing check, so there are no side effects. It lists the specific validation dimensions, though it does not state the form of the result (per-step errors? a single pass/fail?) or whether checking has cost or rate limits.

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?

Two sentences, zero filler, and the non-execution guarantee is front-loaded before the benefit argument. Parenthetical examples are packed efficiently rather than spread over prose.

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?

No output schema and no annotations mean everything must come from the description, and for a validation tool the missing piece is what a failed check returns and how to read it. The purpose and the checks are described completely, but consumers must look to sibling tools to learn the plan/step format that this tool accepts.

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% and the schema only says 'array of object' with no shape at all. The description compensates with mere metaphor ('把计划丢进来') and never says what a step object must contain or whether it matches the format duddy_plan_workflow takes, leaving the caller guessing at the single required parameter.

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 precise verb contrast in '只检查不执行' and names the resource: a plan. It then enumerates the concrete checks (node existence, parameter names, model files), which distinguishes it unambiguously from the apply/rollback siblings such as duddy_apply_step and duddy_rollback_plan.

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?

'不确定的活儿先 precheck 一下，比失败后再回滚便宜' gives a clear condition for use (uncertain work) and a rationale comparing it to the rollback path. It falls short of explicitly naming the alternative tools to call instead once the check passes, so the routing to duddy_apply_step is left implicit.

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