Cursor: assess environment health and freshness

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the agent knows the operation is safe. The description adds two useful behaviors: it 'Launches nothing' (no trigger of builds or jobs) and it operates 'from readback you hold' (no remote fetching). No contradiction with annotations.

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 sentences totaling 24 words, with the core purpose front-loaded and side effects/return stated immediately after. There is no redundancy or filler; every sentence earns its place.

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?

The complex 8-parameter schema is covered in detail by property descriptions, and an output schema exists, so the description needn't repeat return values. It does omit an explicit list of prerequisite readback tools (e.g., cursor_list_builds), though the schema property descriptions mention them. Overall it is adequate given the supporting structured data.

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 88%, so the schema already documents the parameters, including the roles of builds, baseline, observed, and toolchain. The description only groups them into three assessment categories (Build health, source drift, toolchain drift), which adds a bit of conceptual organization but no new per-parameter detail. Baseline of 3 is appropriate given high schema coverage.

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 uses a specific verb ('Judge') and names the exact resources: Build health, source drift, and toolchain drift. It also states the mode ('from readback you hold') and the outcome ('returns a scheduler exit code'), which distinguishes it from sibling tools that inspect definitions or list environments. An agent can tell it apart from cursor_validate_environment_definition or cursor_inspect_environment_definition without opening those tools.

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 phrase 'from readback you hold' implicitly tells the agent that this tool consumes previously gathered data rather than fetching it, and 'Launches nothing' signals it is a pure assessment rather than an action. However, it never explicitly states when to prefer this tool over alternatives like cursor_inspect_environment_definition, nor any exclusions. The usage context is inferable, not stated.

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