verify_variant

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

With no annotations, the description fully bears the burden. It discloses stateless recomputation, approximate timing (~17s), and defines each verdict type (pass/fail/degrade). Adds useful behavioral context without contradiction.

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?

Description is concise with three clear sections: purpose, parameters, return. However, the parameter explanation could be slightly more structured. Overall efficient and front-loaded.

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 the tool's complexity (verification with specific output), the description covers purpose, parameters, return format, and verdict semantics. The presence of an output schema reduces the need to describe return values, but the description still adds value. Complete for a verification tool.

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 0% (description not in schema), but the description explains item_id as the variant ID returned by generate_variants, equals seq, and is a string. This adds meaning beyond the schema's bare type 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?

Description clearly states it independently verifies a variant via stateless Sympy recomputation and provides a verdict. Names specific verb 'verify' and resource 'variant', distinguishing it from siblings like 'generate_variants' and 'persist_variants'.

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 states it must be used before persist ('persist 前须逐题过'), providing usage context. Does not explicitly list alternatives, but the strong precondition effectively guides when to use.

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