hcl_full_build

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, so safety basics are covered; the description still adds real substance: the activate default, that no VM power or CLI deployment happens, and the offline-vs-live replay distinction. There is some tension between "offline builds support durable idempotency" and idempotentHint=false, though the following clause ("live activation is never replayed") largely reconciles it. It never says whether an existing project at project_path is overwritten or what "open in an existing GUI" requires.

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?

Short and front-loaded: the verb-and-resource statement comes first, then the behavioral caveats. The second paragraph is a bit staccato ("activate defaults false" is a fragment) and is not clearly ordered, but no sentence is 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?

For a tool with a deeply nested topology request, a port map, no output schema, and no sibling differentiation, the description is thin. It never says what a successful build produces (plan artifacts? a compiled project directory?), whether the project must already exist, or how this relates to hcl_stage_plan / hcl_open_project / hcl_validate_plan.

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 0% across 7 top-level parameters, and the description only directly explains `activate`. The large nested `request` topology object, `port_map`, `stage_name`, `project_path`, `hcl_pid`, and `idempotency_key` are left for the agent to infer ('open it in an existing GUI' only hints at hcl_pid; 'durable idempotency' only hints at idempotency_key).

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?

"Plan and compile an isolated HCL project, optionally open it in an existing GUI" gives a specific verb pair (plan, compile) plus the resource and an optional side action. It does not, however, distinguish itself from adjacent siblings such as hcl_plan_topology, hcl_stage_plan, hcl_load_plan, or hcl_open_project, so the agent must guess which of these to pick.

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?

"activate defaults false. No VM power or CLI deployment occurs" implicitly tells the agent this tool is not for deployment, and "offline builds" versus "live activation" implies a pre-deploy phase. But no sibling is named as an alternative (e.g. hcl_live_deploy for deployment, hcl_validate_plan for checking), and no prerequisite is stated, so the routing is only inferable.

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