plan_debloat

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the description only needs to add context. It does add the key behavioral fact: this tool produces a reviewable file rather than touching the device, and mutation of the device is deferred to apply_plan. It omits where the file is written and whether an existing plan is overwritten.

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?

Two short sentences with zero filler, ordered by when the agent needs the information: what to do first, then what to do next. Nothing is repeated from the schema or annotations.

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 5-parameter, zero-required tool with no output schema, the description covers the workflow and the safety boundary but leaves the parameter space dark. An agent can correctly decide *whether* to call it, but not confidently choose tier or method from the description alone, which is a meaningful gap for a tool whose output feeds a destructive downstream step.

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 only 20% — just the 'device' parameter is documented — so the description must compensate, and it says nothing about any parameter. The high-stakes choices are entirely unexplained: 'tier' (safe/recommended/all) and 'method' (disable vs remove) have materially different consequences, and include/exclude are not described at all.

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 resource: 'Write a reviewable debloat plan file.' It also implicitly distinguishes itself from apply_plan by framing the plan as a separate artifact from application, so an agent can tell the two apart. It stops short of saying what a 'debloat plan' contains, but the core action is unambiguous.

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?

Gives a clear workflow: generate the plan, show it to the owner, then call apply_plan. That names the downstream alternative and the human-approval gate that selects it. It does not say when *not* to use this tool (e.g. re-running when a plan already exists), so it falls short of full when/when-not coverage.

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