blockrun_chat

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

The annotations are minimal (readOnlyHint=false, destructiveHint=false, openWorldHint=false), but the description adds substantial behavioral nuance: it discloses that mode:'free' is NVIDIA-only and ignored if a model is specified, that thinking is only honored for anthropic/claude-* models, that image inputs work on the native Claude path, and that mixing system param with a role:'system' message causes duplicates. It also explains agent_id budget enforcement.

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 long but well-organized: it front-loads the purpose, uses a clear 'Notable modes' bullet list, and each clause adds information (model mappings, budget, caveats). It avoids repeating schema definitions. Some redundancy exists between the description and the mode parameter's schema description, but the additional model lists justify the length.

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 (11 params, nested multimodal messages, no output schema), the description covers the key decision points: mode routing, direct model selection, thinking behavior, image support, system-prompt duplication, and budget enforcement. It intentionally defers full pricing/availability to blockrun_models, which is acceptable for a chat tool. It does not describe the response format, but that's implicit for a chat endpoint.

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 schema already documents all parameters (100% coverage), so the baseline is 3. The description adds value by enumerating concrete model names for each mode (e.g., powerful → Opus 5, GPT-5.6-sol) and giving direct model ID examples, which the schema enum does not fully specify. It also clarifies free-mode behavior relative to the model parameter.

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 phrase 'Get a second opinion from another AI model, or use a specialized model for a specific task,' clearly identifying this as a multi-model chat tool. It distinguishes itself from siblings like blockrun_image, blockrun_speech, and blockrun_models by focusing on conversational AI access and pointing to blockrun_models only for model listings.

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?

It gives explicit when-to-use context ('Get a second opinion... for a specific task') and provides mode-specific guidance (coding, cheap, free, etc.). It also names an alternative tool ('Run blockrun_models to see all available models with pricing'), making the decision boundary clear.

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