get_table_desc

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

Without annotations, the description carries the full burden. It discloses multi-table query support (useful behavioral context) but fails to indicate read-only safety, return format details, or whether partial matching/wildcards are supported in the search.

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 bilingual format (Chinese with English parenthetical) is efficient and front-loaded. The single sentence conveys both the core action and a key capability without redundancy, though the dual-language format slightly increases length.

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 single-parameter tool, the description is minimally adequate but lacks return value documentation (critical since no output schema exists) and safety annotations. The multi-table mention helps, but more detail on output structure would improve completeness.

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?

With 100% schema coverage, the baseline is 3. The description implies multi-table capability ('supporting multi-table queries') which hints at how the 'text' parameter might be used, but doesn't explicitly document syntax (comma-separated, wildcards, etc.) beyond the schema's basic definition.

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 it searches for 'table structures' and specifically 'table fields' (表字段) based on table names, distinguishing it from sibling get_table_name. However, it doesn't specify the exact schema metadata returned (e.g., data types, constraints, comments).

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?

While it mentions 'supporting multi-table queries' as a capability, it provides no explicit guidance on when to use this tool versus alternatives like execute_sql (which could also retrieve schema) or get_table_name. No 'when-not-to-use' or prerequisites are provided.

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