tf_upgrade_impact

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

Goes well beyond the readOnly/idempotent annotations: it discloses a registry download into a cache, that only temp dirs are written and 'never touches dir', that validation runs on a temp copy, and that the operation becomes offline once the target is downloaded. That is exactly the network/disk side-effect context an agent needs and would not infer from the 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 impact question is front-loaded, the mechanism follows, and the external-tool routing is last. Three dense sentences with no repetition of schema text and no filler.

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?

With no output schema, the description must carry the return-value burden and it does not describe what the impact report contains (format, severity, per-module grouping). Everything else an agent needs — scope, side effects, prerequisites (initialized dir), routing — is present, so the gap is narrow.

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 100%, so the baseline is 3, but the description adds real meaning: 'this configuration uses' clarifies the default include_unused=false scope, and 'confirms with terraform validate on a temp copy' ties to the validate flag. The 'exact version, not a constraint' intent is also reinforced in prose. It does not, however, explain the dir fallback behavior in the body.

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?

Opens with a specific verb+outcome ('what breaks if a pinned provider is upgraded/downgraded to an exact version'), then names the exact comparison scope (arguments, nested blocks, attribute reads, root and installed modules). An agent can tell it apart from tf_get_schema or tf_check_arguments without opening any schema.

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?

States the trigger context (impact of a version change) and explicitly routes one adjacent need elsewhere: 'For the latest version number or upgrade guides, use the official terraform MCP server.' It does not distinguish itself from the sibling tools (tf_get_schema, tf_check_arguments), so no siblings-specific exclusions are given.

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