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

Discloses key behavioral nuances: invoke runs an MCP even when not installed (without adding it to the toolkit), returns authenticate/top-up links for credential/payment needs, and distinguishes one-off vs permanent execution. Also covers auth requirements for mutating actions. This goes well beyond the bare readOnlyHint=false annotation, which is the only structured signal.

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 a single dense block of text that flows without structural breaks. It is informative but wordy, mixing core flow, edge cases, and prompt library guidance in one paragraph. Front-loads the purpose well, but could benefit from bullet points or action-by-action breakdown to improve scannability.

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?

Despite 23 parameters and no schema descriptions, the narrative maps each action to its intent-on parameter needs, covers auth constraints, credential/payment fallback flows, and distinguishes installed vs ephemeral execution. Complete enough for an agent to properly route most queries.

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?

The schema has 21 parameters with zero descriptions sequins full burden. The description explains the central 'action' parameter by walking through each action and its role in the flow, and clarifies key parameters like query, tool_id, arguments, and prompt_* fields. It doesn't thoroughly document every parameter (e.g., immediate, tier_slug), but it covers enough to guide correct invocation in the majority of cases.

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?

Description clearly identifies the tool as the marketplace hub with both discovery and execution modes, and maps each action (search, describe, invoke, install, list_tools, prompt library, etc.) to its purpose. Distinguishes from sibling tools like toolkit_info and sub-tools by naming capabilities and the core flow.

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 explains when to use invoke vs. install ('Use install only to make an MCP permanent... prefer invoke for a single/occasional use'), when to search vs. request_mcp, and states permission requirements for writes (owner/admin). Names alternatives and exclusions, giving clear decision criteria.

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