Code-check definitions and execution / 规范检算定义与执行

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

Annotations only declare destructive/not-read-only/non-idempotent. The description goes well beyond: native-unit vs meters conventions with internal conversions, that a context read is not a lossless snapshot, that full replacements require carrying forward retained values, that empty assignment lists clear data, that verification timeout does not cancel background computation, that completion ≠ passing, and to save before destructive updates. This is exactly the behavioral context annotations cannot express.

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-loaded with purpose and capped by a dense but organized behavioral paragraph; for a 17-operation mega-tool the length is largely earned. It is slightly packed (units, replacement, timeout, and completion caveats run together), but no sentence is pure filler.

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?

Given an output schema exists and each sub-operation carries its own rich description, the top-level text needn't restate returns. It covers the two families, unit conventions, replacement hazards, and timeout semantics well, though it does not mention every branch (e.g. update_vertical_steel_tendon, add/remove_section_reinforcement, manage_check_material), leaving the reader to the schema for those.

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 100%, so the baseline is 3 and the heavy per-field semantics already live in the schema. The description still adds cross-cutting parameter meaning — 'request.operation selects the namespace, units and replacement behavior' plus the native-unit vs meters rule — which is genuine value over the schema's per-branch defaults.

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 opening sentence names a specific verb set and resource ('Set up, edit, execute and inspect code-checking data') and immediately frames the two sub-families (model snapshots vs current concrete-checking context). It then enumerates key operations (setup_concrete_check, run_concrete_check, get_check_data, manage_check_case_file) and explicitly names the siblings edit_properties and analyze_model as different concerns. An agent can route correctly without opening the schema.

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?

Provides both a workflow chain (setup_concrete_check imports → configure → run_concrete_check → get_check_data) and explicit alternatives ('Use edit_properties for structural materials/sections and analyze_model for the structural solve'). It even states when-not: this is concrete code checking, not the general structural solve.

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