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

Annotations only indicate non-read-only and open-world, but the description adds critical behavioral details: invoke works without installation, returns connect/checkout links on auth/payment failures, writes require owner/admin, and the one-off install behind invoke. It also explains what actions do (subscribe/cancel, report_bug, etc.) with no contradiction to annotations.

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?

Despite its length, the description is well-structured and information-dense, starting with a high-level definition, then the core flow, then key caveats, then usage guidance, then the prompt library. Every sentence contributes meaningful operational detail without redundancy.

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 with 23 parameters, 14 actions, and no output schema, the description covers the primary workflow, edge cases (credentials, wallet empty), permissions, and the prompt library. It omits details on some secondary parameters (e.g., immediate, tier_slug) and does not describe response formats, but the core selection and invocation logic is sufficiently complete.

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 burden. It clarifies the meaning of action enum values, tool_id, arguments contextually, and prompt-related parameters (prompt_vars, prompt_slug). However, some parameters like limit, query, immediate, tier_slug, conversation, and cancel_reason are not explicitly addressed, though their names are self-explanatory.

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 identifies the tool as the official mcp.ai marketplace catalog and runner, with a specific core flow (search → describe → invoke). It distinguishes itself from sibling openfinance tools by focusing on cross-MCP discovery and invocation rather than a specific domain.

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?

Explicitly prescribes when to use invoke vs install ('prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT'), describes the search/describe→invoke flow, and covers alternatives like list_tools, report_bug, request_mcp, and the prompt library operations. This goes well beyond vague guidance.

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