panorama_remove_ipsec_candidate

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

Annotations already declare destructiveHint=true, and the description adds substantial context beyond that: it discloses that only 'owned' resources are deleted, that a snapshot is taken before deletion with auto-restore on failure, and that the change remains in candidate config with no commit or push. This gives the agent a complete safety profile for a destructive operation — far beyond the bare annotation.

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?

Three sentences with zero filler, and the destructive warning plus core purpose are front-loaded in the first sentence. Every clause carries distinct information: ownership scoping, snapshot/auto-restore behavior, candidate-only scope. Nothing is redundant with the schema or annotations.

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 destructive two-phase tool with 12 parameters and no output schema, the description covers the critical workflow contract and safety behavior well. Minor gaps: it doesn't describe the shape of the returned removal plan (relevant since no output schema exists), and it doesn't state what to do after a successful apply beyond implying commit/push is a separate step. These are small given the strong 83% schema coverage of parameters.

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 high at 83%, setting the baseline at 3, and the description adds genuine value by explaining the coupling between mode, plan_id, and plan_hash — the plan/apply contract that the schema only hints at with 'Required for mode apply'. It also clarifies what each mode returns or requires. The remaining params (deployment as ownership boundary, serial auto-resolution) are already richly documented in the schema, so no compensation is needed.

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 — 'Two-phase removal of owned IPsec resources' — with the destructive nature flagged up front. The two modes are spelled out (plan returns a plan; apply deletes with plan_id/plan_hash), making it clearly distinguishable from siblings like panorama_apply_ipsec_candidate and panorama_plan_ipsec without opening their schemas.

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 clearly explains the within-tool workflow: run mode 'plan' first, then mode 'apply' with the returned plan_id and plan_hash. 'Candidate configuration only; no commit or push is performed' tells the agent this is a middle step in a pipeline, not a final action. It stops short of explicitly naming alternative siblings (e.g., pointing to a commit tool for the follow-up push), so it doesn't earn a 5.

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