opencode_classify

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

With no annotations provided, the description carries the full burden of behavioral disclosure. The description doesn't state whether this tool makes external API calls, whether classification is local/heuristic or model-based, whether there are side effects (e.g., does it just return a recommendation or does it actually trigger delegation?), or whether it modifies any state. For a decision-making tool, the lack of clarity on side-effectfulness is a notable gap.

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?

Single sentence, zero waste, front-loaded with the action verb. Every element serves a purpose. The description lists the three decision outputs (delegate, model, strategy) which is useful without being verbose.

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?

This is a moderately complex tool (classification decision) with no annotations and no output schema. The description explains inputs and decision axes but doesn't describe the return format, whether the classification is deterministic, or what 'strategy' entails. Given the no-output-schema constraint, the description could be more explicit about the nature of recommendations it produces.

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 100% and the single parameter 'task' is described as 'Task description to classify' which maps directly to the tool's purpose. The description adds minimal meaning beyond the schema, but with only one parameter at full coverage, this is acceptable. The description's mention of 'delegate to OpenCode, recommended model, and strategy' gives context on what the task parameter feeds into.

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 clearly states the verb (classifies), resource (task), and the three outputs (delegate to OpenCode, recommended model, strategy). It's a classification/decision tool distinct from siblings like opencode_send, opencode_start, and opencode_list which perform direct operations. However, it could more precisely distinguish itself from opencode_status or opencode_health which also assess OpenCode state but with different purposes.

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 this is an evaluation/pre-decision tool used before delegating to OpenCode, but doesn't explicitly state when to use it versus alternatives like opencode_send or opencode_command. There's no explicit when-not guidance or mention of alternatives. The context is inferable that this is a preliminary decision tool but not explicitly stated.

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