godot_connect_signal

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

Annotations (readOnlyHint:false, destructiveHint:false, idempotentHint:false) are all neutral/false, so the description bears the full burden of behavioral disclosure. Yet it omits critical behavior: the persist parameter defaults to true, meaning a signal connection silently serializes into the .tscn file on disk. It also fails to mention one_shot auto-disconnection or the disconnect toggle that inverts the entire operation. The description merely restates the mechanism without surfacing side effects.

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?

A single front-loaded English sentence that states the intent in the first word: 'Connect.' Zero filler, no repetition of the tool name, and the object of the action (signal) is front and center. It earns its place as an at-a-glance summary.

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 8 parameters and a divergent behavior-switch (disconnect), this description is far too thin. It doesn't warn that persist:true mutates the .tscn file despite destructiveHint:false, and it doesn't point to siblings like godot_get_signal_connections for pre-verification. The existing output schema covers the return type, so that's not a concern, but the missing side-effect caveat and verification flow leave an agent flying blind.

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%, so the description was expected to compensate — it doesn't. It references the four core parameters (signal_name, source_node_path, target_node_path, method_name) through prose, but entirely omits the four boolean toggles (persist, deferred, one_shot, disconnect). The important detail that persist:true writes to the scene file is buried only in the schema, not surfaced in the description.

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?

The description uses a specific verb+resource: 'Connect a signal from a source node to a target node method.' It clearly captures directionality (source→target) and distinguishes itself from read-oriented siblings like godot_get_signal_connections or godot_get_node_signals. However, it never names or alludes to those siblings, so an agent must infer the distinction from the verb 'connect' vs 'get'.

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?

No guidance is given about when to use this tool versus godot_get_signal_connections (e.g., to verify an existing connection before connecting) or godot_get_node_signals (to discover available signals). There is no mention of prerequisites, like needing an open scene or valid paths, nor any hint about double-connect behavior. The single-sentence description provides zero strategic context for selection.

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