Экспорт и тесты

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, so the safety profile is covered structurally. The description adds mode-level behavior (export writes pack or binary, tests run headless with output parsing) but never warns that export overwrites the file at 'target' or explains the destructive/idempotency implications, leaving a gap for a destructive tool.

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 compact sentence whose clauses are ordered by mode, front-loading the mode enumeration so the agent hits the decision-relevant information first. No filler or redundancy.

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?

With no output schema, the description should carry more of the return and failure story (e.g., what 'разбором вывода' yields, exit codes, overwrite behavior on target). It covers the mode semantics adequately but is thin for a destructive, 7-parameter build tool.

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 71%, and the description meaningfully expands the undocumented enum values (presets/export/test), links pack vs binary to pack_only, and references a custom runner corresponding to test_command. It does not touch timeout_ms, release, or the preset-index convention that the schema itself notes.

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 names the tool's resource (Сборка/build) and enumerates all three operational modes with concrete verbs: listing presets, exporting by preset as pack or binary, and running headless tests. It is clear what the tool does, though it does not differentiate itself from siblings like godot_run or godot_script_check that could also execute things.

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 by the mode breakdown — an agent can infer that mode=test is for running tests and mode=export for producing builds — but there is no explicit when-to-use statement, no guidance on which mode fits which task phase, and no mention of alternatives such as godot_run for non-export execution.

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