DeepMiro

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

Annotations indicate it's not read-only, not destructive, and open-world, which the description aligns with by describing creation and streaming. The description adds valuable behavioral context beyond annotations: it specifies the multi-step process (knowledge graph, personas, simulation, report), streaming of progress updates, and that it returns a final report, which helps the agent understand the tool's execution flow and output.

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 appropriately sized and front-loaded, with three concise sentences that efficiently cover purpose, process, streaming, and output. Each sentence adds value without redundancy, making it easy for an agent to quickly grasp the tool's core functionality and behavior.

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 (multi-step simulation with 6 parameters) and rich annotations, the description is mostly complete. It explains the process and output but lacks details on error handling, performance implications of presets, or how overrides interact with defaults. With no output schema, it could benefit from more on the report format, but the streaming and final return mention provide adequate guidance for agent usage.

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 100%, providing detailed parameter documentation. The description does not add significant meaning beyond the schema, as it doesn't explain parameter interactions or usage nuances. However, it implicitly references 'prompt' and 'document_id' through the scenario example and upload mention, offering minimal additional context, warranting a baseline score of 3.

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 the tool's purpose with specific verbs ('Run', 'Builds', 'generates', 'runs', 'generates') and resources ('full swarm prediction', 'knowledge graph', 'agent personas', 'multi-agent social media simulation', 'prediction report'). It distinguishes from siblings like 'cancel_simulation' or 'get_report' by emphasizing the comprehensive creation process rather than management or retrieval.

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 for running complete simulations with progress streaming, but does not explicitly state when to use this tool versus alternatives like 'list_simulations' or 'search_simulations'. It provides clear context for initiating a simulation but lacks explicit exclusions or named alternatives, though the mention of 'document_id' hints at using 'upload_document' first.

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