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

Beyond the annotations, the description discloses key behaviors: the live check changes no settings, never returns secrets, and the 'not_connected' status means setup was never completed. It also explains the one-connection-per-marketplace model and that credential repair is always done by the user, not through MCP. This is substantial behavioral context that annotations alone do not provide.

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 front-loaded with the core purpose and then packs only high-value operational details: return shape, status semantics, negative guidance, and parameter sourcing. It is longer than average but each clause addresses a real decision an agent would otherwise get wrong.

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 no output schema, the description fully covers the return contract ({integrationId, status, message}), the statuses, and the action to take for error/not_connected. It also covers the connection model, non-destructiveness, secret handling, and parameter sourcing, leaving no critical gap for correct invocation.

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 schema coverage only at 50%, the description compensates by giving marketplace_id's source (list_marketplaces) and clarifying that project_id is optional with a fallback to list_projects when a project is required. It could specify project_id's role more explicitly, but the added guidance meaningfully exceeds the schema.

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 opens with a specific verb ('Verify') and resource ('a marketplace's saved connection'), and explains exactly what the tool does: run a live connectivity/auth check against the channel. It also distinguishes this tool from related connection-test siblings by scoping it to marketplaces and explicitly noting the marketplace_id is the connection.

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 gives explicit when-to-use conditions ('looks connected but items fail' or 'after credentials/OAuth may have expired') and clear when-not-to-use guidance: do not retry configure_marketplace_step, route the user to the browser/UI for fixing credentials. It also points to clone_marketplace for transferring a connection and list_projects for the optional project_id case.

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