yade-mcp

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

With no annotations provided, the description carries the full burden and successfully discloses key behavioral traits: immediate return of task_id, background execution nature, and the requirement to use companion tools for status checking and interruption. However, it could improve by mentioning error handling behavior, output persistence, or concurrency constraints.

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 optimally structured and front-loaded: purpose statement first, return behavior second, lifecycle tooling third, use cases fourth, and alternative tool last. Every sentence serves a distinct function with zero redundancy. The bulleted list for companion tools efficiently compresses what could have been verbose prose.

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 presence of an output schema (which absolves the description from detailing return values), 100% parameter schema coverage, and the complexity of async task management, the description is complete. It covers the execution model, lifecycle management integration, appropriate use cases, and explicit differentiation from synchronous alternatives without over-specifying what the schemas handle.

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 input schema has 100% description coverage, documenting both 'entry_script' as an absolute path and 'description' as a brief purpose. The description refers to 'Python script' generally but does not add semantic details, constraints, or examples beyond what the schema already provides. Baseline 3 is appropriate given the schema's completeness.

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 ('Submit') and clearly identifies the resource (Python script) and execution model (asynchronous in YADE). It effectively distinguishes from sibling 'yade_execute_code' by contrasting 'production simulation runs/long cycles' versus 'quick queries and REPL-style testing', ensuring the agent selects the correct tool for long-running vs. interactive use cases.

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?

Provides explicit when-to-use guidance ('production simulation runs, long O.run() cycles, and any operation that may take minutes or longer') and explicitly names the alternative ('For quick queries... use yade_execute_code'). Additionally, it comprehensively maps the task lifecycle ecosystem by listing the three companion tools needed for polling, interrupting, and browsing history.

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