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

The annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes much further: it warns that submit_all/clean_resubmit_all/remove_all are DESTRUCTIVE and push to the LIVE marketplace, explicitly marks remove_all as PERMANENT, and identifies pre_pair as non-destructive. It also discloses the return shape including status values, which is critical for agents deciding whether an operation succeeded or was refused.

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 every clause delivers high-density operational knowledge: scope, alternatives, per-operation semantics, destructive warnings, confirmation requirements, return fields, and parameter resolution. It is front-loaded with the core scope sentence and uses the sibling tool name early to prevent misuse. No filler or redundant restatement of the tool name.

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 that there is no output schema, the description fully compensates by specifying the exact return object: {integrationId, action, status ('queued'|'done'|'not_allowed'), itemCount, async, message}. It also covers the edge cases an agent must handle, such as not_allowed in Auto-Pilot mode, cooldown refusals, and required confirmation. An agent has enough information to invoke this tool correctly and interpret the result.

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 description coverage at only 50%, the description carries substantial param-documentation weight, and it succeeds. It explains confirm:true for destructive operations, elaborates each operation enum value's behavior, clarifies that project_id is optional only for single-project customers, and maps marketplace_id to the integrationId from list_marketplaces. This far exceeds the sparse schema descriptions.

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 states a specific verb and resource: 'Run a WHOLE-INTEGRATION control-panel operation on a marketplace (acts on every item, not a chosen subset)'. It explicitly distinguishes itself from run_marketplace_item_action, making the tool's scope unmistakable. It also enumerates the exact operations supported, so an agent knows precisely what this tool initiates.

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 guidance: use this for whole-integration operations, and use run_marketplace_item_action for specific items. It also details per-operation conditions such as requiring manual product mode for submit_all, the ~5-minute cooldown for clean_resubmit_all, and the need for confirm:true on destructive operations. This level of operational guidance leaves little to inference.

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