计算产线

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

No annotations exist, so the description carries the full load, and it discloses a critical behavioral trait: a greedy approximation where each item fixes one recipe and byproducts are counted but not recycled. This is exactly the kind of caveat an agent needs to set expectations. It lacks disclosure of cost/performance or failure modes, keeping it from a 5.

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?

Front-loads the core capability and the trigger condition, then the important greedy-approximation caveat, then the output-focus note. Dense but each clause earns its place; the closing sentence about summary tables being 'the point' is well-placed.

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 complex 9-parameter tool with no annotations and no output schema, the description supplies the essential context: what's computed, the approximation caveat, and what the output emphasizes. Missing explicit return-shape detail, but the summary-table orientation largely compensates.

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 89%, so the schema already documents nearly all parameters (ratePerMinute, recipeChoice, tagChoice, rawMaterials, detailDepth, etc.). The description adds framing about summary tables being the focus but little parameter syntax beyond the schema. Baseline 3 is appropriate; note the description says details show 'first 3 layers' while detailDepth defaults to 2, a minor mismatch.

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?

States a specific verb (calculate) and resource (production plan: machines, materials, byproducts, energy) with the exact question it answers. An agent can distinguish it from build_recipe_tree or get_recipes_for_output because the output is a full aggregated line plan, not a recipe tree.

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?

Gives a concrete trigger ('我要每分钟 X 个 Y，怎么建产线') that clearly maps a user request to this tool. It doesn't explicitly name which sibling to use instead for other cases, so it stops short of explicit alternatives/exclusions.

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