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

Despite having annotations (readOnlyHint=false, openWorldHint=true), the description adds enormous value: invoke's side-effect of running tools without installing, the connect link for missing credentials, the checkout/top-up link when the wallet is empty, and the permission requirement that writes need workspace owner/admin. It also explains the one-off install behind invoke and the prompt library's no-login share links. No contradiction with annotations. Annotation Contradiction: false.

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 there is zero fat, but it is one giant wall-of-text paragraph with no structural hierarchy. Helpful typography (CAPS for 'KEY', 'PERMANENT') partially compensates, and the information density is high, yet the reader would benefit enormously from sentence-per-action breaks. It is efficiently written but not well-structured.

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-action enum, 23 parameters, no output schema, no parameter descriptions), the description is remarkably whole. It covers the full state machine (search→describe→invoke), failure/recovery paths (connect/checkout links with retry), permission model, the distinction between one-off invoke and permanent install, list_tools semantics, billing operations, issue reporting, and the entire prompt library subsystem. This is strong coverage for a facade tool of this scope.

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 and 23 parameters, the description carries the full burden and mostly delivers: it explains the action enum semantics thoroughly, clarifies tool_id, arguments, prompt_slug, and the relationship between action values. It loses a point because some non-obvious parameters (report_context, conversation, limit/query semantics, cancel_reason behavior) are left unexplained, and the description could not feasibly cover all 23 params given the length — but the critical action-cluster params are well handled.

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 opens with a precise job statement: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It specifies the exact capability domains ('find an MCP that does X', 'consulta um CPF') and differentiates each sub-action (search vs. describe vs. invoke vs. install). It clearly distinguishes itself from siblings by framing itself as the catalog+runner while siblings like authenticate/show_version are utilities.

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, prescriptive guidance throughout: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use.' It contrasts with alternatives ('To filter by user/workspace, use search_calls_extensive' style clarity through 'list_tools lists what is callable right now'), and it even documents the retry flow after auth/payment links are opened. This is model-guidance gold.

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