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

The description goes far beyond the sparse annotations (readOnlyHint=false, openWorldHint=true). It discloses the key behavioral twist that invoke runs a one-off without installing or bloating the tool list, the credential edge case (returns a connect link), the payment edge case (returns a checkout link and you retry), the flagging of installed_in_toolkit vs installed_in_workspace, and the admin permission model for writes. These are exactly the side-effects an agent needs to know and are not derivable from the 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?

Every sentence earns its place and the density is justified by 14 distinct actions, but the content is delivered as one unbroken wall of text with no bullets, breaks, or headers. The critical distinction (invoke runs one-off vs install makes permanent) is buried mid-paragraph. Information-to-word ratio is high, but scannability for an agent parsing quickly suffers from the lack of structure.

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 of this complexity — 14 actions, 23 params, zero annotations beyond safety hints, no output schema — the description is remarkably complete. It covers the full action surface (core flow, billing, bug reporting, MCP requests, prompt library), addresses return behaviors for key paths (connect link, checkout link, shareable mcp.ai/p/<slug> link), and handles permission and edge cases. Minor residual gaps: exact return formats aren't uniform and a few params remain undefined, but this is strong coverage for the complexity level.

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 across 23 params, the description carries the full compensation burden. It does a strong job on the most important param — action — by narrating each enum value's behavior, and it contextualizes tool_id, arguments, mcp_id, tier_slug, and the prompt_* family through the flow explanations. However, several parameters get zero treatment: message, immediate, conversation, query, and limit are never explained, leaving gaps in a 23-parameter dispatcher.

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 unmistakably specific: it's the official mcp.ai marketplace catalog plus the execution engine for MCPs, with a secondary prompt library. It names exact verbs and resources ('search discovers MCPs by intent', 'describe returns one MCP's full profile', 'invoke RUNS that tool'), and it clearly separates the marketplace domain from the sibling tools (connect, authenticate, show_version). The sheer breadth is organized into a coherent purpose instead of a vague blob.

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?

Outstanding when/where guidance. It prescribes the core flow ('search → describe → invoke'), gives the pivotal decision rule ('Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use'), names alternatives explicitly ('To filter by user...'), and states permission prerequisites ('Writes require workspace owner/admin'). It even enumerates user-intent scenarios ('find an MCP that does X', 'consulta um CPF') that map to the search action.

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