invoke_tool

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

With no annotations, the description must carry the full burden, and it does exceptionally well. It discloses the API key requirement, response composition (output plus latency, version, invocation ID), failure error codes (CIRCUIT_OPEN, RATE_LIMIT_EXCEEDED, TOOL_NOT_FOUND), and 503 alternative-tool behavior. This gives the agent a realistic model of what happens before and after the call.

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 readable and front-loaded with the core purpose, then moves into authentication, response, feedback, and error recovery. Every section contributes useful information, though the error-recovery paragraph becomes slightly detailed. It remains appropriately sized for a proxy invocation tool with no annotations.

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 tool with no annotations, an output schema, three parameters, and a rich failure model, the description covers all the necessary context: prerequisites, parameter semantics, expected response contents, error handling, and post-invocation follow-up. An agent has everything needed to invoke the tool correctly and recover from likely failures.

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 description coverage is 0%, so the description must compensate. It defines slug with a concrete example, version with a default and example, and arguments by pointing to get_tool and explaining they are JSON matching the tool's schema. Examples for slug and version add value, but arguments could have been illustrated more concretely.

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 opens with a specific verb-resource pair: 'Invoke a tool on the invok.it marketplace via transparent proxy.' It clearly targets a distinct action from siblings like get_tool, search_tools, and submit_outcome. The marketplace scope and proxy mechanism remove ambiguity about what this tool does.

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 gives explicit workflow guidance: check get_tool first to understand the input_schema, then invoke, and afterwards use submit_outcome for quality feedback. It also instructs on failure recovery, telling the agent to switch to alternative tools or retry after the suggested delay. This goes well beyond implied usage.

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