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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes well beyond that, disclosing the preview-versus-apply contract (read-only unless confirm:true), exactly what it mutates (adds LMCP to apps missing it, repairs dead-command entries), and the boundary of its authority (permissions, app restarts, unsafe configs, update installs surface in needs_you with the exact step). That is unusually rich disclosure for a tool that can write.

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?

Front-loaded with what it checks before explaining what it fixes, and every clause is load-bearing (scope, mutations, preview contract, needs_you boundary, usage trigger). It is dense and long, but not padded.

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 complex multi-domain diagnostic-and-repair tool, the description covers scope, mutation behavior, the confirmation gate, and the escalation path; an output schema exists to carry return values. An agent has everything needed to call it correctly.

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?

Only one parameter and schema description coverage is 100%, so the schema already fully documents confirm. The description's "Read-only PREVIEW unless confirm:true" reinforces the same semantics rather than adding new meaning, so baseline 3 is appropriate.

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 scope: it checks LMCP dependencies (connected AI apps, macOS permissions, integrations, pending updates) and fixes what it safely can. This is much more than a tautology. It does not explicitly differentiate itself from the many sibling diagnostics tools (run_diagnostics, lmcp_state, lmcp_upgrade_diagnostics, permissions_status), so it lands at 4 rather than 5.

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 when LMCP 'doesn't work' in some app" gives a clear triggering condition, and the read-only-unless-confirm framing clarifies the interaction model. It never names or excludes the closely related diagnostic siblings, so it stops short of explicit when-not/alternative routing.

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