codex_start_thread_compaction

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

Describes the operation as starting compaction (async) and returning actionId. No annotations exist, but the description gives essential behavioral context. Minor gap: no mention of failure modes or side effects.

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?

Two sentences, no fluff, front-loaded with purpose and usage. Every word adds value.

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?

Provides essential flow but lacks details on preconditions (e.g., thread must be active), error conditions, or output format beyond actionId. Output schema exists but description doesn't leverage 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 coverage is 0% and the description adds no meaning for thread_id, project_id, or timeout_seconds. The agent must guess parameter roles beyond the raw schema.

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?

Clearly states the tool starts context compaction for a known thread and returns an actionId. Differentiates from sibling tools by specifying the next step to poll compaction status.

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?

Explicitly says to use after active work is terminal and instructs to poll codex_get_thread_compaction_status next, providing clear context for when and how to use.

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