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

The description discloses significant behavioral details beyond the annotations: it warns that installing 'RESTARTS LMCP (the AI client briefly reconnects)' and that confirm=true is required. The annotations only say readOnlyHint=false and destructiveHint=false, so the restart side effect and the confirm requirement are crucial additions that the description covers thoroughly.

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 slightly verbose but well-structured: it front-loads the core purpose, then explains the side effect and parameter usage. Every sentence adds information, and the flow is logical. It could be trimmed slightly, but it's efficient for the complexity involved.

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 an output schema exists (though not shown) and the annotations provide some safety hints, the description covers the main behavior, side effects, and parameter semantics. It doesn't mention prerequisites like network connectivity, but that's likely not essential for an agent deciding to call it. The description is complete enough for correct invocation.

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 input schema already describes both parameters (confirm and check_only) with 100% coverage. The description adds value by linking confirm to the restart side effect and clarifying that check_only avoids download/restart, which goes beyond the schema's individual parameter descriptions. This enriches the semantics without redundancy.

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 the tool's action: 'Checks for and installs a newer LMCP version'. It specifies the resource (LMCP app itself) and explicitly distinguishes it from editing data ('not editing any of your data'). This is a specific verb+resource combination that makes the purpose unambiguous, even without naming siblings.

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 provides clear usage context: it explains that installing requires confirm=true and that check_only=true is for availability checks without download/restart. It implicitly differentiates from data-editing tools, but does not explicitly name alternative tools like lmcp_state or lmcp_upgrade_diagnostics. Still, the two modes are well explained, giving an agent actionable guidance.

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