Cursor: inspect environment definition

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds behavioral context beyond that: it states that the tool returns a 'Normalized view' and explicitly notes 'Scripts are digests.' This informs the agent that the output is transformed (not raw) and that scripts are represented as hashes, which is useful for interpreting results. This goes beyond the structured 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?

The description is a single, tightly written sentence. It front-loads the core purpose ('Normalized view of a Cursor environment definition') and then enumerates the included components without any filler. Every clause adds informational value, and the 'Scripts are digests' note is a meaningful qualifier. No redundancy or wordiness.

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?

Given the tool has an output schema (so the return structure is defined externally), the description covers what the inspection yields: a normalized view of install/start, terminals, ports, MCP policy, build paths, and snapshot input, plus the digest representation of scripts. It does not mention return format or error cases, but those are likely handled by the output schema and the tool's runtime. The description is adequate for an inspect operation.

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 every property in the 'definition' object has a description explaining its semantics (e.g., text is JSONC, source has an enum with 'delegated-saved' labeled as untrusted evidence, repoRoot must be '.'). The tool description adds no additional parameter-level guidance – it only lists what the definition contains. Baseline 3 is appropriate since the schema alone is fully self-explanatory.

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 specifies a clear verb ('inspect') and resource ('environment definition'), and adds that it provides a 'Normalized view' with a concrete list of contents (install/start, terminals, ports, MCP policy, build paths, snapshot input). It does not explicitly contrast with sibling tools like validate or diff, but the term 'inspect' and 'Normalized view' imply a read-only, processed reading, which differentiates it enough for most agents.

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?

There is no guidance on when to use this tool versus alternatives. Sibling tools such as cursor_validate_environment_definition, cursor_diff_environment_definition, and cursor_get_environment_configuration exist, but the description never mentions them or states conditions that would make one preferable. The agent is left to infer from the name and the generic verb 'inspect' that it is for reading a definition, which is not explicit enough for confident selection.

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