godot_lsp_rename

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

Annotations declare readOnlyHint=false, consistent with a mutation, and destructiveHint=false, meaning the operation is considered reversible via LSP undo. The description adds context by implying the operation mutates symbols across multiple files, which is a significant side-effect-bearing behavior worth flagging. However, the description doesn't cover important behavioral traits like failure modes (symbol not found), file-saving requirements, or whether the change is immediately persisted — leaving meaningful gaps for a refactoring operation.

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?

Six words, zero waste, with the operation, resource, and scope all accurately front-loaded into a single clause. Every word earns its place. An exemplary model of how concise a description should be.

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?

This is a complex, cross-file refactoring tool with 4 parameters, 0% schema description coverage, and no output schema in the definition. Yet the description provides no context about expected failure modes, preconditions (e.g., LSP must resolve the symbol), or behavior on ambiguity. For a tool that can rewrite the user's codebase across multiple files, the absence of any guidance beyond six words leaves a critical gap in an agent's ability to use it safely.

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 must compensate, yet it mentions none of the four parameters. While the nested LSPRenameInput schema does contain helpful descriptions (e.g., '1-indexed line number of the symbol to rename'), the top-level tool description itself is silent on parameter meaning. An agent must dig into nested schema definitions, which rescues usability but gains no credit for the tool 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, 'Perform cross-file semantic symbol rename,' names a specific verb (rename), a resource (symbol), and a scope (cross-file) that distinguishes it from all 190+ siblings. The word 'semantic' differentiates it from text-based find/replace, and 'cross-file' signals the operation's project-wide blast radius. An agent can distinguish this from godot_lsp_query and godot_validate_script immediately.

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 context is clearly implied through 'cross-file semantic' — the agent can infer this is for renaming symbols that span multiple files. However, the description never explicitly names alternatives or exclusion conditions (e.g., 'for single-file text replacement use X'). Unlike the HIGH calibration example which explicitly routed to search_calls_extensive, this provides guidance only through implication.

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