Gemini Mcp Add

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the return contract ('Returns CLI stdout') and a real behavioral constraint (headers only valid for http/sse), and the verb 'Add' signals a mutation. It is silent on persistence of the config, conflict behavior for duplicate names, permission needs, and side effects on scope, which for a 13-parameter mutating CLI wrapper leaves meaningful gaps.

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 compact sentences, purpose and the CLI anchor front-loaded, followed by the transport rules and return contract. The terse 'transport: stdio|http|sse' shorthand is efficient and no sentence is wasted. Minor density: cramming two conditional rules into one sentence slightly reduces readability.

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 not be explained and the description reasonably does not. But this is a 13-parameter tool with 0% schema description coverage, and the majority of parameters (scope defaulting to 'project', trust, include/exclude_tools, env_vars, timeouts) are unexplained anywhere — an agent cannot confidently populate them from this definition alone.

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 0%, so the description must compensate, and it does add real meaning for the most critical parameters: it defines the transport enum values and, crucially, explains that command_or_url means an executable under stdio but a URL under http/sse — semantics not derivable from the schema. It still leaves roughly ten parameters (scope, trust, args, env_vars, timeouts, include/exclude_tools, description) completely undocumented in both schema and description.

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 states a specific verb+resource — 'Add an MCP server via gemini CLI (gemini mcp add ...)' — which clearly distinguishes it from siblings like gemini_mcp_list and gemini_mcp_remove. It is not merely a restatement of the name; it identifies the concrete CLI operation performed. It stops short of a 5 because it never explicitly names the sibling tools it complements.

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 conditional usage rules for parameters ('for stdio pass executable, for http/sse pass URL' and 'headers are only valid for http/sse'), which is genuine how-to guidance. However, there is no explicit statement of when to choose this tool over gemini_mcp_list/remove, nor any prerequisites such as needing the CLI installed or the config scope implications. Usage is implied by the verb, not spelled out.

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