hcl_explain_plan

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds one genuinely useful trait, "without an LLM" (deterministic, non-model-generated explanation) and hints that output reports limits on what can be proven. It does not say what happens on an invalid plan or what the explanation contains.

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?

One short sentence with no filler; the key qualifier ("without an LLM") is placed where it is visible. Only the cloudy phrase "evidence boundaries" costs a point.

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 ~50-definition input schema and no output schema, the description says nothing about the return value's shape or how the explanation is structured, which is the main thing an agent needs to decide whether to call it. The burden left by absent output schema is unmet.

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?

There is a single parameter with 0% schema description coverage and a large nested TopologyPlan structure, so the description carries the full explanatory burden and provides none. It calls the input a "saved plan" while the schema takes a full plan object, not a saved-plan reference, which is ambiguous. No mention of required fields, schema_version, or size constraints.

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?

"Explain a valid saved plan" names a verb and resource, but "explain" is vague about what the output actually contains, and "evidence boundaries" is unexplained jargon. It does not distinguish itself from nearby siblings like hcl_validate_plan, hcl_estimate_plan, or hcl_fix_plan, all of which also consume a plan and produce analysis.

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 when-to-use guidance: nothing says to explain rather than validate, estimate, or fix a plan, nor what condition makes a plan "valid" enough to explain. The reader must infer the tool's role in the workflow from its name alone.

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