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

The annotations only carry readOnlyHint=false with no safety detail, so the description carries full weight — and it delivers. It discloses the one-off invoke behavior ('runs the tool pontualmente... without adding the MCP to the toolkit'), the connect-link and checkout/top-up retry semantics for missing auth/empty wallet, and the owner/admin requirement for writes. All that goes well beyond the structured annotation block with no contradiction.

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?

A dense ~350-word single paragraph with no line breaks, bullets, or a crisp front-loaded summary. Nearly every sentence earns its place given the 14-action surface pinned to a single tool, so it is information-dense rather than padded, but the wall-of-text presentation seriously hurts scannability for an agent parsing it.

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 14-action router with no output schema, it covers the primary flows well: the search→describe→invoke pipeline, install vs invoke trade-offs, auth/payment edge cases (connect link, top-up link, retry), permission requirements, and the separate prompt library. It partially discloses return behavior (connect/checkout links, prompt text, shareable slug), though it never details what describe or list_tools return.

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 23 params at 0% schema coverage, the description must compensate heavily. It does explain the pivotal action enum and its values (search, describe, invoke, install, list_tools, prompt actions) and ties tool_id/arguments to the invoke flow. But individual parameter semantics — limit, immediate, tier_slug, cancel_reason, conversation, prompt_vars — remain undocumented, leaving gaps the schema does not fill.

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?

States its full role explicitly: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then enumerates all 14 dispatch actions, making the broad surface unambiguous. Clearly distinct from siblings like authenticate, connect, and tribunal_trt24_processo_consultar, so there is no confusion about when to reach for this tool.

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?

Provides an explicit recommended flow: 'action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool.' Also gives a clear decision rule between the two overlapping actions — 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT' — and points to list_tools for what is callable right now.

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