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

The description discloses key behavioral traits beyond annotations: invoke runs tools even when not installed, without bloating the tool list; it returns connect links for missing credentials and checkout/top-up links for empty wallets; writes require workspace owner/admin. It also explains that search/describe flag installation status (installed_in_toolkit vs installed_in_workspace). These are critical behavioral details that the annotations (readOnlyHint=false, openWorldHint=true) do not cover, and there is no contradiction with the 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?

The description is long but information-dense, with a logical structure: core flow, key caveats (invoke behavior, auth/payment links), usage guidance, and prompt library. It front-loads the primary purpose and the most critical operational detail (invoke works without installation). While a few sentences are packed, they all add value; the length is justified by the tool's complexity and 0% schema coverage. It is not repetitive or bloated.

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 complexity (23 parameters, no output schema, no schema descriptions), the description is remarkably complete: it covers the main use cases, the action flows, permission requirements, error-recovery scenarios (connect/checkout links), and the prompt library sub-features. It also explains the distinction between permanent installation and one-off invocation, which is crucial for correct usage. No obvious gaps remain for an agent to select and invoke the tool correctly.

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 carries the full burden, and it does well: it explains the 'action' enum categories (search, describe, invoke, install, list_tools, subscribe/cancel, report_bug, request_mcp, and prompt functions) and their purpose. It also explains the core flow parameters (query, mcp_id, tool_id, arguments) implicitly, though it doesn't detail exact types or defaults. Given the large parameter count (23) and 0% coverage, the description provides essential meaning for the most important parameters, but some parameters like 'tier_slug', 'immediate', 'conversation', and 'prompt_targets' are not explained.

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 marketplace as the in-platform catalog and execution mechanism for MCPs, covering capability requests and the core search-describe-invoke flow. It explicitly distinguishes the tool from siblings by naming list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt library functions with their specific roles. The verb 'discovers', 'returns', 'runs', and 'lists' are specific to actions, making the purpose 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 when-to-use guidance: use 'invoke' for one-off runs even when the MCP is not installed, use 'install' only for permanent toolkit additions, and prefer invoke for single/occasional use. It also clarifies when to use subscribe/cancel, report_bug, request_mcp, and the prompt library functions. Exclusions and alternatives are named, such as 'prefer invoke for a single/occasional use' versus 'install only to make an MCP PERMANENT'.

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