Upgrade planner

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

Annotations cover the safety profile (readOnlyHint true, openWorldHint true), so the description's burden is reduced, and it still adds real behavioral context: the result is a prioritized plan whose per-line targets come either from a computed work order or from the minimal fixing version per vulnerability. With no output schema, it carries return-value information reasonably well, though it never describes the shape or ordering of the returned plan.

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 tight sentences, with the core deliverable front-loaded before the computation details and the trigger sentence last. The parenthetical is dense but each clause carries information; nothing is redundant.

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 read-only tool with four optional params and no output schema, the description supplies the two computation modes and the natural-language trigger, which is most of what an agent needs to decide to call it. It leaves the structure of the returned plan and the meaning of risk levels undescribed, a modest gap given the absent output schema.

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 each parameter (package, include_dev, risk_threshold, max_recommendations) already documents itself including defaults and the enum. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 opening clause states a specific resource — a prioritized upgrade plan — and explains the two ways it is computed (a computed 'work order' versus the smallest version fixing each vulnerability). That is enough for an agent to recognize the tool. It loses a point because internal jargon ('4DA app', 'manifest vs lockfile fix', 'per-line targets') is never unpacked and no sibling tool is named to contrast against.

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?

Ends with an explicit trigger: 'Call when the user asks what to upgrade.' That is clear, actionable usage context. It offers no when-not guidance and does not distinguish itself from adjacent siblings like upgrade_impact or vulnerability_scan, so it stops short of a 5.

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