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

Annotations declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds real behavioral context beyond them: the default is a non-mutating preview, the write is gated on confirm, configs are edited rather than authored by hand, and the restart/new-session requirement for changes to take effect. It also enumerates the four per-client outcome states the agent should expect.

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?

Purpose and scope are front-loaded in the first clause, and the sentences carry substantive information (gating, outcomes, restart step). The parenthetical client catalog is somewhat redundant with the schema's id enum, but the overall density is high and little is wasted.

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 two-parameter, conditionally-mutating tool this is complete: the agent knows the default preview behavior, how to commit changes, how to scope to a single client, what the response will signal per client, and what follow-up action the user needs. The output schema already covers return structure, so the description's per-client summary is complementary rather than required.

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 description coverage is 100% and both parameters are fully documented there (including the enumerated client ids and the 'omit to do all installed' behavior), so the description's mention of an optional single `client` id and the preview/confirm gate largely restates structured data. Baseline 3 is appropriate; the description adds no syntax or format detail the schema lacks.

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 (adds/configures) and resource (Local MCP entries in MCP-capable app configs), names the source catalog and example clients, and explicitly contrasts with 'manual JSON editing'. An agent can immediately tell this is the tool that wires LMCP into other apps, distinct from lmcp_install_upgrade or setup_install.

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?

Clearly states the trigger conditions: it writes only when confirm:true, otherwise it is a read-only preview, and it optionally narrows to one client. It also routes the agent to a companion step ('Pair with list_missing_permissions for fully agent-driven setup'), though it does not describe when NOT to use it or profile side effects of repeated runs.

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