godot_evaluate_expression

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

With 0% schema review coverage, the description says 'safely' — a single word bearing the huge load of a serious claim about side effects and sandboxing that remains unsubstantiated. It does not tell you whether the expression can mutate the scene tree, what gets returned, or what the 'safety' boundary really is. The description does not use the annotation block leading to the API user; a single sentence is a half-sheet of behavioral floor for an escape hatch that needs a contract.

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?

One eight-word sentence does the work, front-loading the most informative element. It is a model of restraint, no filler; it does not spend a single word that is not earned. The only reason not to give a 5 is that a definition this short could spend a little more time and still be concise, but that is a mountaineer's route.

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?

The output schema and rich parameter metadata carry a lot of the expressiveness, so the description does not have to describe the return behavior in depth — the schema does not cover error handling, side effects, or the safety model, and it should say something about them. On a balance for a currently neutral feature with a capable authoring story this covers it, but the heaviest user questions (is it safe? does it mutate?) go unanswered.

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?

The schema tediously documents all the parameters with examples and use cases for expression, so described behavior is the strongest in the suite. The description adds no value to parameter understanding: it does not mention node_path, input_variables, or the wrapping params object, even though the given 0% coverage should put the burden of supplying semantic context on it. On its own the schema anchors the parameter model / the description adds nothing.

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 is a single, precise verb-object pair ('Evaluate ... expression') that names the resource (arbitrary GDScript expression) and scopes it with 'at runtime', which a knowledgeable user can distinguish from a sibling like validate_script. It is terse, but every word adds a nuance: it does not just be a tool name, and it is abundantly clear what it does. It earns top marks by adding the qualification 'safely at runtime' where peers that just repeat the identifier are common. The word 'arbitrary' and the example-rich schema make up for the lack of a dedicated caveat.

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 only usage signal is 'safely at runtime', which is implicit at best; it does not say when to use this versus the many siblings or when to prefer something like validate_script or LSP_Query. There is no guidance that this is an escape hatch versus a sandboxed alternative, and no caveat that the user should prefer this over a typed sibling.

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