Terraform apply

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

No annotations are provided, so the description carries the full burden and does so well: it flags HIGH RISK mutation, explains that the no-approval path is non-destructive (computes plan, records pending approval), and discloses approval lifecycle traits (single-use, expiring, parameter-bound). This is far beyond what a bare 'apply' would convey.

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?

Four tight sentences with the risk warning and the two-phase contract front-loaded; no filler. Dense but readable, and every clause adds operational information.

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?

Output schema exists so return-value documentation is unnecessary, and the description still names the key return (approval id). Combined with the risk warning and approval lifecycle, an agent has everything needed to call this correctly and safely.

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 0%, so the description must compensate; it fully explains approval_id semantics (optional, single-use, expiring, must match exact parameters, absence means no apply). working_dir is never explained, which is the one remaining gap, but the high-risk parameter is covered.

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?

States a specific verb and resource ('mutates real infrastructure', Terraform apply) and immediately clarifies its two-phase nature, which separates it from terraform_plan's pure-preview role. An agent can tell what this does and when it would fire without opening the 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?

Explicit conditional workflow: call without approval_id to compute a plan and register a pending approval, then call again with the returned approval_id to execute. It also states the human review happens out-of-band, so the agent knows not to wait on this call for the mutation to occur.

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