create_section

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

Annotations give only readOnlyHint=false, destructiveHint=false, so they communicate little. The description compensates by disclosing the full complexity of the tool: sec_info layout varies by sec_type, all parameter orderings for 20+ types, and which parameters are conditional (box_num/box_height/symmetry/chamfer_info for concrete box girders). It doesn't discuss error behavior or what happens on invalid combinations, but for a parametric creation tool the parameter-layout disclosure is the key behavioral transparency, and it is provided in depth. A small deduction for not mentioning side effects or failure modes.

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 description is long, but the length is earned: every section type entry lists different parameter orderings that cannot be omitted. It is well-structured with visual separators (基本形状, 混凝土/组合, 钢结构带肋) and ends with examples. The 'Args:' formatting is a bit unusual for an LLM-facing tool (reads like Python docstring), but it is organized and scannable. One minor deduction for the docstring-style format and a small amount of redundancy (e.g. Chinese parentheticals repeating the English terms).

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 tool with 8 parameters, 20+ section types, and no output schema, the description is remarkably complete. It covers all parameter semantics, conditional parameter applicability, and provides examples. The remaining gaps: it doesn't state what the tool returns on success/failure, doesn't clarify whether mat_combine is formatted as ratios (e.g. percentages), and doesn't explain chamfer_info string format for concrete box girders. Given the complexity, this is strong but not perfect.

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%, so the description must fully compensate, and it does substantially. It defines sec_type as a Chinese enum with all allowed values, gives the exact sec_info element order for each type, and explains mat_combine, box_num, box_height, symmetry, and chamfer_info. However, it does not fully explain the default behavior of sec_info (nullable with default null) or whether it is required for all types, so there is a small remaining gap. Overall it adds enormous meaning beyond the bare schema.

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 clearly states the tool creates a cross-section and explicitly says it is 'one tool for all parametric section types' (创建截面). It distinguishes itself from non-parametric alternatives by naming siblings create_polygon_section, create_line_width_section, and create_section_from_properties. The purpose is unambiguous and directly differentiates from the sibling tools.

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?

The description explicitly explains when to use this tool vs alternatives: 'For non-parametric sections use: create_polygon_section, create_line_width_section, create_section_from_properties'. It also gives detailed per-type parameter guidance, including which parameters apply only to concrete box girders. This is exemplary usage guidance far beyond the minimum.

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