Add control

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false) and the description is consistent with them, so no contradiction. The description adds useful semantic behavior (input_id may reference device IDs, other CTRL IDs, or CONSTANT; math functions with setpoint+trip_direction act as boolean gates), but says nothing about error handling for invalid function_type/parameter combinations, duplicate IDs, or required permissions.

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?

Front-loaded with the action, then a compact catalogue of function types and input rules; for 25 function types and 17 parameters the density is justified and no sentence is filler. The one downside is that the run-on FUNCTION_TYPE enumeration is hard to parse and could be broken into lines, which keeps it just short of 5.

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 17-parameter, 25-variant creation tool with no output schema, the description covers the domain vocabulary well, and the absence of a return-value explanation is acceptable. However, it omits preconditions (must referenced devices/controls exist?), behavior on invalid combinations, and interaction with update_control, leaving real gaps for a tool of this complexity.

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%, giving a baseline of 3, and the description genuinely adds cross-parameter semantics the schema does not: it maps each function type to the parameters it consumes (DEADBAND -> setpoint+setpoint2+on_bound, PID -> target_value+gains, CUSTOM -> ramp_id, TIME_DELAY -> delay, X_OF_N -> n). This tells an agent which of the 17 params matter for a chosen function_type, exceeding individual property descriptions.

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 a CTRL control logic element") and then enumerates the complete space of FUNCTION_TYPE variants with their dependent parameters, so an agent knows exactly what object class is being created and which configurations are valid. This makes it unmistakable against siblings such as add_device, add_vent, update_control, and remove_control.

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?

Usage is only implied: the bulc-mcp rules pointer (DEVC-004, DEVC-006 -> bulc_knowledge_search "<id>") hints that rules should be consulted, and the operation is obviously the creation counterpart to update_control/remove_control, but the description never explicitly says when to prefer this tool, what preconditions must hold, or when not to use it. No explicit exclusion or alternative-routing guidance is given.

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