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

Annotations only give readOnlyHint=false and openWorldHint=true. The description adds substantial behavioral context beyond these: the invoke-runs-without-install semantics ('runs the tool pontualmente (one-off), without adding the MCP to the toolkit'), auth-required link behavior, empty-wallet checkout links, workspace-owner/admin permission requirements, and the retry-after-user-action flow. No contradiction with annotations (readOnlyHint=false is consistent with the described writes/mutations).

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 long but information-dense — it front-loads the core value proposition, uses a 'KEY:' marker to highlight the most important nuance about invoke, and organizes content logically (marketplace flow → permissions → prompt library). It avoids filler and every sentence carries meaning for a tool with 23 params and 14 actions. It loses a point for being a dense wall of text with the minor 'pontualmente' oddity and some redundancy around invoke's behavior.

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 (23 params, 14 enum actions, no output schema), the description covers the conceptual model well: discovery/execution distinction, persistence semantics, billing/auth states, role-based permissions, and the secondary prompt-library feature. Some gaps remain: no error handling guidance, no response shape hints (especially relevant with no output schema), and no mapping of all action/params combinations. Still, it is notably complete for the main workflows.

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 carries the full burden, and it does add meaning for several key params (action=search/describe/invoke, 'pick the right tool_id', arguments via '{{variables}} filled', prompt_vars for the prompt flow, cancel_reason enumerations implicitly for subscription cancellation). However, 23 params exist and many (limit, immediate, tier_slug, conversation, request_details, cancel_reason codes) are never mentioned. The narrative provides strong semantics for the core flow but leaves the long tail undocumented.

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 explicit about the specific verb+resource: it is 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly differentiates the core flows (search → describe → invoke), contrasts invoke vs install, and even notes the secondary prompt-library feature. The description meaningfully distinguishes this omni-tool from potential siblings by laying out its action-based 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: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use', and contrasts invoke vs list_tools and search_* vs get_prompt. It explicitly names internal alternatives with clear routing logic (e.g., 'request_mcp asks us to build a NEW MCP when nothing fits'). This meets the bar for explicit when/when-not/alternatives.

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