Compare two snapshots

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

With no annotations, the description carries the full burden. It discloses side effects (writes .md and .json files), what it filters out (noise like ids and audit info), and the failOnDrift error behavior. It does not explicitly state that the operation is read-only on the snapshots, but 'offline diff' strongly implies no mutation. It lacks details on permissions or prerequisites, but the disclosed behavior is substantial.

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 with the core purpose and scope front-loaded. The second sentence is dense but efficient, covering output and the failOnDrift behavior. No fluff or repetition. Slightly long second sentence but acceptable.

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 tool has 7 parameters, no output schema, and no annotations. The description covers the main output (report files) and the failOnDrift semantics, but leaves ignoredKeys unexplained and does not mention return value details for normal (non-fail) cases. It also omits whether the operation requires a specific working directory or project context. Given the complexity, it is adequate but not fully complete.

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 coverage is 71% (5 of 7 params have descriptions). The description adds meaning for failOnDrift (pipeline gate usage) but does not explain ignoredKeys, which lacks a schema description. includeDiffs and strictVariables are already described in the schema, so the description adds no value there. The description partially compensates for the uncovered parameter but misses ignoredKeys.

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 ('compare'), resource ('two snapshot folders'), and enumerates exactly what is compared (solution version, per-agent YAML, flows, connection refs, env vars, unpublished changes). It also distinguishes itself from potential siblings by calling out 'offline diff' and writing a report, which sets it apart from online comparison or drift-check 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 description implies usage context: 'offline diff' suggests it is for static snapshot comparison rather than live environments, and the mention of 'failOnDrift returns an error result (for pipeline gates)' explicitly ties it to CI/CD pipeline usage. However, it does not name alternative tools like cs_compare_environments or cs_check_drift, nor state when to prefer this over them, leaving some ambiguity.

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