Chenji Affect

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

With no annotations, the description carries the disclosure burden. It clearly explains what the tool produces and constrains input size and language options, which covers the main behavioral surface for an analysis tool. It does not mention side effects such as data retention or authentication, but those are less critical for this kind of text-analysis operation.

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 two dense sentences with no filler. The tool's action and output types are front-loaded, followed by concise parameter guidance, making it easy to parse quickly.

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 tool with an output schema and an unrelated sibling, this description is nearly complete: it covers purpose, outputs, input limits, and supported language values. It could be slightly stronger by mentioning usage exclusions or any special response interpretation, but nothing essential for invoking the tool is missing.

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%, but the description compensates fully. It explains the text parameter as input up to 2000 characters and lang as an optional parameter accepting 'zh' or 'en', which adds meaningful semantics that the raw schema lacks.

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 begins with 'L1 Affect Extraction: analyze text into...' and enumerates four concrete output types: an 8-dimensional emotion vector, emotion texture labels, causal intent classification, and a natural-language state description. This makes the tool's purpose unambiguous and distinctly separate from the unrelated sibling tool generate_avatar_params.

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 gives clear invocation context by specifying that text is input up to 2000 characters and lang is optional with 'zh' or 'en' values. It does not explicitly state when not to use the tool or point to alternatives, but the only sibling tool is unrelated, so there is no real routing ambiguity.

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

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

There are no annotations, so the description must carry the burden of behavioral disclosure. It does disclose that one call aggregates multiple output packages and that an L2 key tier is required. However, it does not mention failure behavior, side effects, latency, or what happens when the key tier is insufficient.

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 a single dense sentence with no wasted words, and the key pipeline identifier is front-loaded. It earns its length but uses heavy jargon (blendshape/AU/curve, adapter payload, atmosphere package) that could reduce quick comprehension.

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 an output schema present, describing return values is less necessary, and the description does add useful context about the pipeline level and key tier requirement. However, it omits parameter guidance and any explicit relationship to the sibling tool, leaving an agent to infer important selection and input details.

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%, and the description never explains what `text` should contain, its format, length, or role in the pipeline. The only clue is the tool name and the schema's `text` property, so the description does not compensate for the missing parameter documentation.

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 identifies a specific pipeline ('L2 Avatar Driving Pipeline') and states that a single call returns blendshape/AU/curve parameters, lighting and material packages, adapter payload, and L1 affect analysis. This clearly differentiates it from the sibling analyze_text by positioning it as the L2 generation tool rather than L1 text analysis.

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 implies when to use the tool: when L2 avatar driving parameters are needed and the account has a key tier including L2. However, it does not explicitly contrast it with analyze_text or state when NOT to use it, leaving the selection logic somewhat implicit.

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