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

With annotations present (readOnlyHint=false, openWorldHint=true), the bar is lower, but the description adds valuable context beyond them: one-off execution semantics ('without adding the MCP to the toolkit and without bloating the tool list'), auth/payment edge cases (connect link, checkout/top-up link then retry), and permission requirements ('Writes ... require workspace owner/admin'). No contradiction with annotations — arguably impossible to confirm contradiction given the formatting, but the content seems consistent with readOnlyHint=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?

A single dense paragraph (~300 words) for a 23-param, 14-action dispatcher. It is front-loaded with the core message and every sentence earns its place, but the prompt-library section is tacked on and would benefit from bullet separation. The length is justified by the tool's complexity.

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 an extremely complex dispatcher with no output schema, the description covers the discovery flow, install-vs-invoke decision, permission model, billing/auth edge cases, and the separate prompt library. It does not precisely specify search/describe return formats, but coverage is thorough for 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?

Schema description coverage is 0%, so the description must compensate, and it does: the action enum (14 values) is mapped to flows, and mcp_id/tool_id/arguments are explained for describe and invoke. A few params (immediate, tier_slug, conversation, limit) remain undocumented, but the highest-leverage semantics are well covered.

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 specific, unambiguous statement: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It maps intent phrases directly ('find an MCP that does X', 'consulta um CPF') and fully distinguishes itself from siblings like report_bug, connect, and authenticate by centering on catalog discovery plus execution.

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?

Exceptionally explicit when-to-use guidance: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT', the ordered core flow (search → describe → invoke), and action-specific triggers ('list_tools lists what is callable right now', 'request_mcp asks us to build a NEW MCP when nothing fits', 'subscribe/cancel handle per-MCP billing'). This clearly frames decision boundaries.

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