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

Beyond the minimal annotations (readOnlyHint false, openWorldHint true), the description discloses key behaviors: invoke works even when the MCP is not installed ('runs the tool pontualmente'), returns connect/checkout links on credential or payment needs, and that writes require workspace owner/admin. It also explains the one-off nature of invoke and the permanent nature of install. This significantly adds behavioral context that annotations do not contain.

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 about 180 words, long but justified given the tool's complexity. It is front-loaded with the core concept and flow, then details key behaviors and specific actions. Each sentence adds value—no fluff. The structure is logically ordered (concept → flow → key nuances → actions). It is appropriately sized for a meta-tool with 14 actions, though it could be broken into sections for easier scanning, earning a 4.

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?

Given the tool's high complexity (23 parameters, 14 actions, no output schema), the description provides a strong overview covering all key aspects: the marketplace core, invoke/install distinction, auth/payment handling, prompt library, and permission requirements. It does not detail response structures for every action, but it does mention what returns (e.g., describe returns full profile, publish_prompt returns a shareable link). It is reasonably complete for the scale, though an output schema or per-action response examples would improve it, hence a 4.

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 a 0% schema description coverage, the description must compensate heavily. It links major parameters to actions: 'action=search', 'describe returns one MCP's full profile', 'invoke RUNS that tool with tool_id and arguments.' It also mentions prompt-related parameters (prompt_body, prompt_vars) implicitly in the prompt library section. However, it does not explicitly explain every one of the 23 parameters (e.g., prompt_targets, cancel_reason), though it gives enough context for the agent to infer from the action descriptions. The description adds substantial meaning but leaves some parameter details implicit, scoring 4.

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 clearly states the tool's purpose: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It goes beyond a generic statement by detailing the core flow (search → describe → invoke) and listing specific actions (install, subscribe, search_prompts, etc.), which distinguishes it from sibling tools like connect or report_bug. The verb+resource combination is precise and unambiguous.

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 guidance on when to use different actions: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use.' It also specifies that 'list_tools lists what is callable right now' and that writes require admin. The alternative is clearly stated: 'prefer invoke for a single/occasional use' vs 'install only to make an MCP PERMANENT.' This offers clear context and exclusions.

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