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

Beyond the destructive and read/write annotations, it discloses irreversibility, cascading feed deletion, webhook unregistration, the absence of a restore tool, the confirm_required HTTP 400 no-op, and the response shape. These details tell the agent exactly what to warn about and what to expect, with no contradiction of 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 destructive warning is front-loaded, and nearly every clause supports safe selection or invocation without filler. However, the single dense paragraph and nested parentheticals make the confirmation, response, and parameter-resolution details harder to scan than they would be in short sections or bullets.

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 high-risk destructive operation with no output schema, it covers impact, consent, invocation requirements, non-destructive failure behavior, return values, and parameter acquisition. The agent has the operational context needed to invoke it safely and handle the documented errors.

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?

Although schema description coverage is 0%, the description meaningfully documents all three parameters. It explains the confirm safety gate, where to obtain marketplace_id, and when project_id can be omitted, including the project_id_required error and how to recover.

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?

It opens with the exact operation and resource, "Delete a marketplace," then defines its blast radius: syncing stops, the marketplace leaves the list, feeds are hard-deleted, and webhooks are unregistered. That scope distinguishes it from siblings such as delete_feed, pause_marketplace, and the item-removal tools.

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?

It restricts use to an explicit user deletion request, requires user confirmation before calling with confirm:true, and explains the safe failure mode without confirmation. It also provides a concrete pre-call workflow by routing ID discovery to list_marketplaces and missing-project resolution to list_projects.

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