shapeshift

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

The description discloses that empty server_id unmounts, and calling shapeshift() with no arguments unmounts and kills the process. However, it does not explain side effects on existing tools, network requirements, or safety implications, which is a gap given no annotations.

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 concise, uses code examples effectively, and front-loads the primary action. It could be more structured with a brief list of parameters, but overall it reads well without extraneous content.

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?

Despite the output schema existing, the description does not cover the 'keep' and 'server_args' parameters, leaving gaps for a tool with 6 parameters and no annotations. The core functionality is clear, but completeness is reduced by missing parameter explanations.

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 description adds meaning to 4 of 6 parameters (server_id, tools, confirm, source) through examples and notes, but fails to explain 'keep' and 'server_args'. With 0% schema description coverage, the description compensates partially but misses two parameters.

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 'Mount an MCP server's tools at runtime' and provides concrete examples showing mounting, lean mounting, and unmounting. This distinguishes it from sibling tools (auth, auto, call, search, status), which are unrelated.

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 offers clear context with examples for mounting, unmounting, and lean loading, and mentions when to use 'confirm' for community sources. While it lacks explicit when-not-to-use statements, the tool's unique role among siblings makes usage intuitive.

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