Install Matrix

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

Annotations declare openWorldHint=true, readOnlyHint=false, destructiveHint=false. The description adds meaningful behavioral context beyond these: 'Deterministic, no model call' clarifies it's not generative/AI-dependent, and it discloses the exact return shape (clients array with method, snippet, config_path?, notes?). It also reveals edge-case handling (Antigravity name normalization), which is valuable transparency.

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 dense but well-structured: it front-loads the primary action and value proposition, then gives usage context, then input/return shape. It's on the longer side but every sentence carries information — client quirks, determinism, defaults, and return format all justify their presence. Slight redundancy between schema param examples and description examples, but minor.

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?

The tool is moderately complex (nested input object, multiple output variants), and the description covers the action, output shape, parameter semantics, and special case handling. Without an output schema, describing the return structure ({clients:[...], count}) is helpful. It could add more on error cases or what happens with unsupported transports, but given 100% schema coverage and a clear description, this is adequate.

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 100%, with detailed per-parameter descriptions (e.g., server_url required URL, name normalization to lowercase a-z0-9 for Antigravity, auth enum meanings). The description adds value by mapping parameters to behavior: transport defaults to streamable-http, auth bearer variants add Authorization headers. It also documents default behaviors (name derived from URL host) beyond what the schema states.

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 uses a specific verb ('Generate') with a clear resource (MCP install snippets for ~29 clients) and explicitly states the tool's unique value: per-client config-key traps already encoded. It distinctively differentiates itself from siblings by naming exact client quirks (Antigravity, Gemini CLI, AnythingLLM, etc.) and defining the deterministic no-model-call property.

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?

Explicit 'Use when' guidance is given: 'when you or your user needs to wire ANY MCP server into a client without hunting per-client docs.' It clearly scopes the use case and differentiates from alternatives by noting the value proposition over manual doc-hunting. The when-not/exclusion case isn't explicitly stated, but the use case is concrete enough that exclusions are implied.

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