Export files

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

Annotations already flag destructiveHint=true and idempotentHint=true, so the description's key contribution is the nuance that existing files are kept unless overwrite is true — that materially clarifies how destructive it actually is in practice. It also discloses the per-format scope (animation file contains all animations, model only for Java). It does not cover partial-failure behavior or whether parent directories are created, which is why it isn't a 5.

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?

Two sentences, zero filler, and the artifact list is front-loaded before the overwrite caveat. Every clause carries distinct information about what gets written or what happens on collision.

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 five-optional-parameter write tool with no output schema, the description covers what is produced and the overwrite policy, which is most of what an agent needs. The notable gap is return behavior — whether it reports the written paths or a partial-success status — which matters given multiple optional artifacts can each fail independently.

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, but the description earns more by binding parameters to meaning the schema lacks: the model parameter is implicitly Java-only, and each path parameter is tied to a specific output artifact and extension. The overwrite flag's consequence (keep vs replace) is also restated behaviorally rather than just as a default value.

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?

Opens with a concrete verb ('Writes') and names the resource precisely: the open project's geo, animation, model and texture files. It even annotates the format of each artifact (.geo.json, .animation.json, .png), so an agent knows exactly what will be produced. It stops short of explicitly contrasting with sibling tools, though the write-to-disk framing is distinct enough on its own.

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 implied rather than stated: the agent must infer that a project should be open first, and there is no explicit 'use this instead of X' routing. The one real conditional it does give is valuable — the model export is 'Java projects only' — but the absence of any when-not or prerequisite statement keeps this at minimum-viable.

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