load_library

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

With no annotations, the description carries the full burden and does well: it discloses that the loaded code survives reload_api and new namespaces via automatic re-loading, and that ~/.inventor-mcp/startup.py or INVENTOR_MCP_STARTUP is applied to every Inventor. It omits failure behavior (missing file, syntax errors) and any security notes about arbitrary code execution.

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 sentences, front-loaded with the core action and the persistence guarantee. Dense but every clause adds information; the parenthetical example is the only mild padding.

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?

An output schema exists, so return values need no explanation, and the description covers scope (this Inventor's namespace), persistence semantics, and the global startup mechanism. Error handling and namespace collision behavior remain unaddressed, keeping it just short of complete.

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 coverage is 50% — 'instance' is documented in the schema and the description adds no more, while 'path' is undocumented in both. The description implies the path points to a Python file but gives no guidance on absolute vs relative resolution or required extension.

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 a specific verb and resource ('Run a Python file into this Inventor's execute_python namespace') and immediately establishes the distinguishing trait — the file is kept and auto-reloaded — which separates it from the one-shot execute_python sibling.

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 a clear use case ('For helper functions and cached objects you would otherwise redefine every time') and describes the automatic startup.py variant. It does not explicitly say 'use execute_python instead when you want a one-off run', but the contrast is strongly implied.

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