新增或编辑角色场景道具状态

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

Goes well past the annotations: it describes a fingerprint-based concurrency check (expected_sha256 must match for edits, must be absent for creates), promises unmodified images/models/styles/bindings are preserved, names the underlying POST states upsert, and explicitly says no image generation is triggered. The annotations already cover safety and idempotency, so this added context is genuinely useful rather than redundant.

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-loads the create-vs-edit branch in the first clause, then packs patch contents, preservation guarantees, and the save mechanism into short semicolon-separated clauses. No filler and no repetition of schema or annotation data.

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 mutation tool with 7 parameters, a nested patch object, and no schema documentation, the description supplies the essential contract: mode selection, fingerprint requirement, editable fields, and what is preserved. An output schema exists so return values need no explanation; only operation_id's role and valid asset_type values are unaddressed.

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 description coverage is 0% across 7 parameters, so the description carries the load: it defines state_id's two modes, expected_sha256's required absence on create, and the editable keys inside patch (state_name, description, episode_nos, reference_images) with a format constraint for reference images. project_id, asset_type, asset_id, and operation_id remain unexplained, which leaves a real gap.

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 pair and resource (create or edit an asset's state) and immediately splits the two modes by state_id presence. This is enough to tell it apart from siblings such as pavo_script_create_asset or pavo_script_rename_asset, which operate on the asset itself rather than on a state record.

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?

Gives explicit conditional usage: omit state_id (and omit expected_sha256) to create, pass a real state_id plus the matching states fingerprint to edit. It also states the required patch fields for the create branch. It doesn't name an alternative tool or an exclusion case, which keeps it from a 5.

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