run_tool

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

Discloses a refusal gate (spec_confirmed=true) and a required preceding call for dynamic params. The destructiveHint annotation already covers destructiveness, and the description adds concrete behavioral constraints without contradicting it.

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?

Three short sentences; the main verb+object, the most important warning, and a concrete parameter example are packed with no filler. The critical prerequisites are 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?

The description covers the essential invocation path: call get_tool_choices for generated params, set spec_confirmed=true, and supply params JSON. With an output schema present and annotations covering safety, remaining gaps such as where names come from are minor.

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?

The example of params as a JSON object and spec_confirmed=true adds meaning to the otherwise bare schema, which has 0% coverage. However, it calls params a 'JSON object' while the schema declares a string type, which can mislead an agent into passing an object instead of a JSON-encoded string.

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 'Execute a solidified tool by name with given parameters.' This names a specific verb and target and clearly differentiates from siblings like solidify_tool (creation), list_tools, and get_tool_choices.

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?

Gives explicit prerequisites: call get_tool_choices first for parameters with choices_from / source: query:*, and notes the tool is refused unless spec_confirmed=true. It does not explicitly compare with execute_code or list_tools, but the required conditions are clear.

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