cli_upgrade

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

Annotations already carry the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), and the description adds value beyond them by disclosing that destruction only happens on explicit opt-out of the dryRun default, plus the behavioral trait that upgrades are delegated to the CLI's native mechanism rather than a managed install. It doesn't detail side effects (global state, network needs) of that native mechanism, but given annotation coverage the bar is lower and it clears it. No contradiction with annotations: the tool is destructive-capable and the description's default-safe mode is consistent with that.

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?

A single 19-word sentence that front-loads the behavior (plan vs execute) and the safety default before the mechanism. Every word earns its place, and the plan/execute contrast is stated before the 'native update mechanism' qualifier. This is appropriately sized and structured.

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 destructive-capable tool with no output schema, the description falls short of fully complete: it never says what a plan actually returns, whether the native updater can run non-interactively (an agent-execution risk), what happens on failure, or whether prerequisites like the CLI being installed exist. The 100%-covered schema and accurate annotations carry much of the load, so this is adequate but with clear gaps on the execute path.

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%, so the schema already documents all four parameters, setting the baseline at 3. The description adds only marginal meaning: it restates the dryRun default and clarifies that the operation targets one CLI at a time, but it does not enrich target semantics or explain when to set timeoutMs beyond what the schema provides.

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 names a specific verb pair (plan/execute), a concrete resource (an upgrade for one provider CLI), and a distinguishing qualifier ('native update mechanism'). The 'one provider CLI' phrasing plus the mechanism scopes it apart from sibling tools like cli_versions (listing) and provider_version_guard (guarding), so an agent can tell what this tool does without opening the schema.

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 gives clear invocation context: by default the tool only produces a plan (dryRun=true), and execution requires explicit opt-in via dryRun=false. This tells the agent how to use the tool safely in its default mode. It does not state exclusions or route to alternatives (e.g., checking versions via cli_versions), but since this is the only upgrade tool among the siblings, the mode guidance is the primary usage signal.

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