Stage Anim Save

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

With no annotations, the description carries the disclosure burden well: it names the write target, states the prior file is moved to history/ (a real side effect), notes the file is consumed by Blender renders, and describes the error case ('the server refused it') and the emitted anim_saved event with its payloads. It stops short of permission requirements or whether a missing scene errors.

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?

Front-loaded with the action and destination, then side effects, then replies and events — a sensible ordering with no filler. The parenthetical 'page command: anim_save' and the event syntax are dense but each sentence carries information.

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?

An output schema exists, so return values needn't be explained, yet the description adds the reply shape {ok, path} and event emissions, plus history/ archiving. Main remaining gap is prerequisite context — whether the scene must be loaded/started first, which matters for a staged-scene 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 0% for the single 'scene' parameter, so the description must compensate. It does partially, by showing scene is interpolated into the path scenes/<scene>/anim.json, but it doesn't say whether scene is a slug, display name, or must already exist — leaving the parameter's format ambiguous.

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?

States a specific verb and resource with destination path: saves keys and growth spans to scenes/<scene>/anim.json, with the old file archived to history/. That distinguishes it implicitly from the sibling setters (stage_key_set, stage_growth_set), though it never names those siblings or says it is the persistence step after editing them.

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 only implied: an agent can infer this should be called after keys/growth spans are edited, since those get written to anim.json. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g. versus stage_anim_clear or stage_scene_export).

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