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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses critical behaviors: invoke works even when the MCP is not installed and does not bloat the tool list, install makes tools natively available, write operations require workspace owner/admin, and invoke returns connect/checkout links when credentials or payment are needed. These details are essential for an agent to predict tool behavior safely.

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 and front-loads the main purpose, then uses arrows to map the core flow. It is longer than necessary and could be structured with lists or headings, but every sentence contributes meaningful information. Minor redundancies exist (e.g., repeating 'invoke works even when the MCP is NOT installed').

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 complex tool with 14 actions and no output schema, the description covers most critical aspects: billing, auth, permissions, prompt library, and the distinction between one-off and permanent installs. However, it omits the 'resume' action entirely and does not specify return formats for search/describe results, which could be important for an agent to parse the response.

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?

With 0% schema description coverage, the description compensates well for the key parameters: it explains the action enum (search, describe, install, invoke, etc.), mcp_id/tool_id/arguments, and prompt-related parameters (prompt_body, prompt_vars, prompt_slug). However, many parameters like limit, query, immediate, cancel_reason, and conversation are left implicit or undescribed, leaving gaps for a 23-parameter tool.

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 opening sentence clearly states the tool's role: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' This is a specific verb-resource combination that distinguishes it from sibling tools like authenticate or show_version. It also explicitly covers capability requests and prompt library functionality, leaving no ambiguity about scope.

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' and 'Use install only to make an MCP PERMANENT in the active toolkit.' It also outlines the core flow (search → describe → invoke) and handles edge cases with connect/checkout links and retry instructions. This surpasses what annotations or schema alone offer.

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