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

Annotations already set destructiveHint=true. The description adds concrete behavioral context: 'Wipes the previous broken install' confirms destruction, and 'Returns a new session_id — poll with check_status' explains the lifecycle. No contradictions. Could mention permanence of wipe or failure modes, but sufficient for safe usage.

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?

Three well-structured sentences. First states the action, second explains the effect and return value, third tells when to use. Every sentence earns its place with no redundancy or fluff.

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 retry tool with no output schema, the description covers the return value (session_id), follow-up action (poll with check_status), and sources for the required server_token. It is complete enough for an agent to use correctly. Minor improvement could be adding error handling hints for invalid tokens, but not essential.

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 coverage is 100% with good descriptions. The description adds value by clarifying the conditional semantics of optional parameters (ip/password only if user discovered errors) and reinforcing server_token as authorization. This context goes beyond the schema's static 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 clearly states 'Retry a failed deployment' with specific actions: wipes previous broken install, runs fresh deploy on same server, returns new session_id. It distinguishes from sibling tools like register_and_deploy by focusing on retrying a failed deploy using a server_token.

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 tells the agent when to use this tool: 'Use this when the user reports a failed deploy or pastes a server_token.' It also provides conditional guidance for optional parameters (ip/password only if user discovered wrong credentials) and implies alternatives via sibling tools.

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