Compose · Kernel Reply

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds significant behavioral context: it is a 'final human-facing composition' with a ΔS≤0 constraint (no state change), and it supports multiple modes. There is no contradiction; the description enriches transparency beyond annotations.

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 short and front-loaded with key information. It uses jargon like 'ΔS≤0' that may be obscure but is concise. Every sentence adds value. Minor deduction for the jargon density.

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?

Given the tool has 10 parameters and an output schema exists (not shown), the description covers overall purpose and pipeline position but lacks parameter documentation. It is adequate for understanding when to use the tool but insufficient for parameter-level decisions without the schema. The output schema may compensate, but description doesn't reference it.

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%, so the description must compensate. It mentions modes and style but introduces 'format' and 'style' as modes not present in the enum (schema lacks 'style' and 'format' as enum values, though style is a separate parameter). Other parameters (message, actor_id, language, etc.) are not explained at all. This inconsistency and lack of detail limit its helpfulness.

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 explicitly states the tool's purpose: 'Final human-facing composition' and positions it as the last step in a pipeline ('Call LAST after observe/think/judge'). It lists specific capabilities (citations, tone, ΔS≤0) and modes, clearly distinguishing it from siblings like arif_judge and arif_seal.

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 explicit guidance on when to call ('LAST after observe/think/judge') and when not to ('not mid-pipeline'). It also states what the tool is not a substitute for (arif_judge, arif_seal), providing clear exclusion criteria. This helps the agent select the correct tool in the pipeline.

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