particle_manage

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

With no annotations provided, the description takes full responsibility for disclosing behavior. It does this thoroughly: mentions that all write ops create nodes and sub-resources in a single undo action, that restart is runtime-only and not undoable, and that unknown override keys return INVALID_PARAMS rather than being silently dropped. It also details auto-creation of ProcessMaterial and QuadMesh, which is crucial for understanding 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?

The description is long but every sentence carries specific technical content. It is well-structured with bullet points per operation, making it easy to scan. While it could be trimmed slightly (e.g., repeating 'auto-creates ProcessMaterial' for GPU emitters), the density of useful information justifies its length. It is front-loaded with the core purpose and then elaborates appropriately.

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 description covers all operations, parameter semantics, error behavior, response reporting ('response reports applied_main / applied_process / applied_draw'), and cross-type constraints (GPU vs CPU, 2D vs 3D). It handles edge cases like overrides routing and invalid keys. Given the tool's complexity and the minimal schema, this description is exceptionally complete.

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 input schema is minimal (op, params, session_id) with 0% schema description coverage. The description compensates magnificently by explaining every operation's parameters in detail, including property names, types, defaults, and per-type variations (e.g., 'GPU gravity requires {x, y, z} even for gpu_2d'). It also explains the canonical call shape and flat-op compatibility alias, providing meaning far beyond the schema.

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 opens with 'Particle systems (GPUParticles2D/3D, CPUParticles2D/3D)', immediately identifying the specific resource. It then enumerates all operations (create, set_main, set_process, etc.) with a clear verb for each, making it unambiguous what the tool does and distinguishing it from sibling manage tools like animation_manage or material_manage.

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 description clearly implies when to use the tool: whenever particle emitters need to be created, configured, or restarted. It provides context for particle-specific behavior (e.g., GPU vs CPU, 2D vs 3D) and even notes edge cases like 'GPU gravity is a Vector3' and 'cpu_* types reject draw overrides.' However, it does not explicitly state 'use this instead of X' or provide exclusions versus sibling tools, so it falls slightly short of a 5.

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