bw_add_process_chain_plswitch

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

With no annotations, the description carries the full behavioral burden and does so: it discloses that the edit is in-place (read model, insert node with INLINE process variant, PUT back), that validation happens before any write (only cockpit-offered, active, planning-enabled aDSOs are accepted, others refused), and that the operation is idempotent for identical type+datastore sets. It also documents edge_mode defaulting to 'both' so the switch-back runs on failure, and explains transport_request auto-selection versus $TMP behavior.

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?

Dense and front-loaded: the core purpose, mode semantics, and constraint about needing an anchor point come first. The later sentences on inline editing, aDSO validation, edge_mode, idempotency, and naming conventions are all substantive, though the description is long and could be tightened slightly without losing meaning.

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 an 11-parameter mutation tool with no annotations and no output schema, the description covers the important behavioral aspects: in-place edit mechanics, validation-before-write, idempotency, edge handling, and transport recording. It does not describe return values or error shapes (no output schema exists), and activation side effects are left mostly to the schema's 'activate' parameter description, which is a minor gap.

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; the description adds genuine meaning by explaining the rationale behind mode selection, the mutual exclusivity of before/after/predecessor, the fact that 'bracket' uses 'around', and that datastores must be active and planning-enabled. It stops short of describing every parameter (e.g., activate, description, transport_request details are only in schema), but the additional context on the routing parameters is meaningful.

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 (add planning mode switch steps / PLSWITCHL / PLSWITCHP to an existing Process Chain RSPC) and explicitly ties the operation to planning-enabled aDSOs, which separates it from siblings like bw_set_adso_planning_mode and bw_add_process_chain_program. The explanation of what a switch step actually does (switch to load mode before a DTP, back to planning mode after) removes any ambiguity about the operation.

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?

Gives explicit mode semantics (load, plan, bracket), the required anchor for single-step modes (exactly one of before/after/predecessor), and the reason there is no automatic append point. It also names the bracketing use case explicitly ('around', usually the DTP) and explains the default edge_mode behavior, so an agent knows both when and how to invoke each variant.

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