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

Annotations declare openWorldHint=true (interacts with an open world of external entities), but the description states 'No network call -- this is a pure offline algorithm plus small public lookup tables', i.e. a closed, deterministic result domain. These directly conflict. The rich extras it does give (format-only semantics, check-digit algorithm, no-existence-proof caveat) are otherwise valuable, but the contradiction governs under the scoring rule.

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 purpose and standard, then layers scope and the format-only caveat. Slightly dense (example query phrasings, dual-language code names), but each sentence adds actionable information rather than 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?

With no output schema, the description fully compensates by specifying what a valid code decodes to (registration authority, entity type, province), the algorithm basis, and the format_only_note returned in every response. Nothing an agent needs to interpret the result is missing.

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 100% for the single 'code' parameter, and the description adds no format/syntax detail beyond the schema's own note on case-insensitivity and whitespace trimming. Baseline 3 applies when the schema fully carries parameter meaning.

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+resource (formats and validates/decodes the 18-char Unified Social Credit Code) with the governing standard (GB 32100-2015) named. An agent can immediately tell this apart from siblings like company_register_search or validate_claim.

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?

Explicitly scopes when to use it ('is this a valid Chinese company code', 'decode this USCC', 'which province') and, crucially, when its answer is NOT sufficient ('validates FORMAT ONLY... confirming existence requires a live registry lookup this tool does not perform'), routing existence checks to registry siblings.

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