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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses key behaviors: invoke runs one-off without installing or bloating the toolkit, returns connect/checkout links when credentials/wallet are missing, writes require workspace owner/admin, and search/describe flag installation status. It also details the prompt library's shareable-link behavior. This is rich contextual disclosure that goes well beyond what annotations provide.

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 a single dense paragraph of ~230 words, but every sentence carries meaningful information relevant to choosing and invoking actions. It is information-dense, though a bulleted or sectioned structure would improve scannability. No fluff or repetition is present.

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?

For a tool with no output schema, the description partially explains return behaviors (e.g., invoke returns connect/checkout links, publish_prompt returns a shareable link, describe returns a full profile). However, it does not specify return formats for search, subscribe, uninstall, or report_bug, nor does it explain several actions' parameter requirements. Given the tool's complexity and 0% schema coverage, important gaps remain, but the high-level decision flow is well covered.

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%, and the description only partially compensates. It references `mcp_id`, `tool_id`, `arguments`, `query`, and all action enum values, but leaves many parameters undefined, such as `immediate`, `tier_slug`, `conversation`, `request_name`, `cancel_reason`, `prompt_body`, `prompt_vars`, `prompt_targets`, and `report_context`. An agent invoking actions with these parameters would lack guidance about their meaning or required format.

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 is explicit and specific: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It names the primary verbs (search, describe, invoke, install) and distinguishes the tool's role from siblings by covering the full lifecycle of MCP discovery, execution, and installation. It even identifies overlapping functionality with sibling tools (e.g., report_bug) while making its own broader scope clear.

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 provides explicit when-to-use guidance: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', 'request_mcp asks us to build a NEW MCP when nothing fits', and it explains the core flow search → describe → invoke. It distinguishes between similar actions (invoke vs install, search_prompts vs get_prompt) and gives conditional behavior for credentials/payment, which helps the agent select the right action.

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