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

The annotations already declare read-only, non-destructive, idempotent, closed-world behavior. The description adds useful behavioral context beyond that: it returns either an MCP tool to call or a page to send someone to, and with no task it lists every tool.

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, covers the return behavior and the no-task case, and uses concrete examples without wasting sentences.

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 discovery/routing tool with no output schema, the description gives enough information to invoke it correctly: what it returns, how it routes between MCP and browser usage, and what happens when no task is supplied.

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%, so the schema already defines task, limit, and callableOnly. The description still adds meaning by explaining the empty-task behavior, which is not stated in the schema and is important for invocation.

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: find the WarmInboxes free tool for a described task, then say how to use it. The examples (checking headers, cleaning CSV, spam prediction) and the MCP-tool-vs-browser-page distinction make its purpose distinct from the many specific sibling 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 clearly explains the main use case: give it a task and it routes to either an MCP tool or a browser page. It also specifies the no-argument behavior ('Call with no task to list every tool'), but it does not explicitly say when to prefer this over calling a known sibling directly.

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