opencode_question_reply

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

Annotations declare destructiveHint: true and openWorldHint: true, so the agent already knows this mutates state. The description adds minimal behavioral context—'Answer' implies a one-way submission, and 'per question' hints at cardinality, but it doesn't disclose side effects beyond that. It adds no new behavioral traits that annotations don't cover, so a 3 is appropriate.

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 concise, two sentences, with the core purpose front-loaded. No unnecessary words. It could possibly add a hint about multiple questions in one call, but as is, it's efficient and well-structured. Loses a point for not explicitly hinting at the array-of-arrays shape in the first sentence, but the structure is solid.

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?

Because an output schema exists (per context signals), return handling is covered elsewhere. The description covers the essential input format but omits prerequisites, such as the requirement that a question request must be currently active or that this action is final and cannot be retracted. For a destructive tool with a nested answers structure, more context would help an agent use it correctly, so a 3 is fair.

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 only 33% (only directory is described). The description's phrase 'Supply one array of selected labels or free text per question' clarifies the answers parameter structure (array of arrays of strings) and its alignment with questions. However, it doesn't explain requestId beyond what the schema implies (a required string), and directory already has its own schema description. It partially compensates for the low coverage but leaves requestId semantics unexplained.

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 tool's purpose: 'Answer an OpenCode question request.' This specifies a verb (answer) and a resource (question request), distinguishing it from sibling opencode_question_reject. It is clear and specific, though it doesn't explicitly differentiate from other reply/send tools, so not a perfect 5.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention that it should only be used for pending questions, nor does it point to opencode_question_reject for the reject case. Sibling tools exist but are not referenced. Usage context is only implied by the resource name.

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