cloudpin_switch_plan

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

Annotations only declare readOnlyHint=true. The description adds valuable context: 'Nothing is run,' 'the same plan as cloudpin switch --json without --yes,' pinned IDs are shown in full while active-login IDs are shortened, and there is a 'what to do by hand' fallback. This is behavior beyond what annotations provide. It doesn't describe output format details, but it goes well past the annotation baseline.

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?

Four sentences, each carrying real content: the trigger, the output, the equivalence to the CLI --json form, ID display rules, and the don't-execute rule. The trailing user-call sentence reinforces the don't-run rule already stated, which is slightly redundant, but overall it's front-loaded and efficient.

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 single-parameter read-only planning tool with no output schema, the description covers trigger, output semantics, ID display, and execution safety. The one gap is that it doesn't explain the plan's internal structure or how an agent should present it beyond 'show the commands,' but the essentials for correct invocation are present.

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 schema has a single optional 'cwd' parameter with 100% description coverage ('Project folder; defaults to the current one'). The description doesn't mention cwd at all, so it adds nothing here. Baseline 3 applies when the schema does the work.

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 states a specific verb-and-resource: it produces a remediation plan of exact commands for moving each CLI to its pinned account on a .cloudpin.yml mismatch. It's clear about what's returned ('the exact commands... or what to do by hand') and distinguishes itself from siblings by not being a status/check tool. However, the sibling tools (doctor, check, status) are not named, so an agent must infer the routing.

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?

It gives a clear condition ('on a mismatch with .cloudpin.yml') and explicitly states the user-facing constraint: 'Show the commands to the user and never run them yourself.' It doesn't explicitly say to use cloudpin_check first to detect the mismatch, which would make the when-to-use sharper, but the triggering context is well specified.

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