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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds real behavioral context beyond them: the 6-hour polling cadence, that only tools/list is invoked with no login and no tool calls, and the exact status vocabulary (answering, needs a login, not reachable). That is precisely the operational context an agent needs to interpret staleness and status values.

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?

Two sentences, front-loaded with the scope, then the return fields, then the routing hint and the negative constraint. The parentheticals are dense but every clause carries information.

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?

An output schema exists, yet the description still summarizes the returned fields and status values, and it closes the one ambiguity a listing tool creates (that it does not return tool descriptions). Nothing needed to call it correctly is missing.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate. It correctly avoids inventing filter options that the empty schema does not support.

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?

States a specific verb and resource ('List the public MCP servers whose tools apiwatch checks every 6 hours') and enumerates exactly what is returned (status, tool count, last check, last observed change). It also distinguishes itself from the sibling mcp_server_changes by framing itself as the index of what that tool can answer about.

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?

'Use it to see which servers mcp_server_changes can answer about' explicitly names the alternative and the condition that selects it. The parenthetical 'tools/list only, no login, no tool calls' plus 'Returns no tool descriptions' pre-empts the most likely misuse (expecting tool-level detail).

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