execute_tool

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. However, the tool is described as executing other tools (including potentially mutable ones), which contradicts readOnlyHint. The description provides no extra behavioral context (e.g., whether proxied tool outputs are returned, error handling, permissions). The contradiction and lack of detail leave the agent poorly informed.

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 very short (one line) and front-loads the service name and purpose. However, it lacks structure (e.g., separate sentences for when, how, what). It is minimally acceptable but could be better organized for agent readability.

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?

The tool is a meta-tool with complex behavior (dynamic invocation of other tools) and no output schema. The description fails to explain that the tool returns the result of the proxied tool, how errors are handled, or that tool_name must be from discover_tools. For the tool's complexity and the absence of output schema, the description is insufficient.

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% with clear parameter names and types. The description 'tool_name + params' adds no meaning beyond the schema. For the params object, no details on required subfields or structure are provided. Baseline score of 3 is appropriate given full schema coverage, but the description does not enhance parameter understanding.

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 states it is a proxy execution tool for tools discovered via discover_tools, naming the two required parameters (tool_name and params). This clearly identifies the tool as a meta-tool for dynamic invocation, distinguishing it from domain-specific siblings like search_law and get_law_text. However, the mixed Korean-English phrasing and lack of explicit 'execute another tool' phrasing slightly reduces clarity for non-Korean agents.

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 implies usage after discover_tools by mentioning 'discover_tools 결과 도구를 프록시 실행'. No explicit guidance on when to use this tool versus directly calling the specific tool, nor any exclusion cases. An agent can infer the intended workflow, but explicit alternatives and when-not-to-use conditions are missing.

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