task_retry

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false. The description adds useful behavioral context by stating it stores metadata only, does not execute an agent, and is isolated by project_path, though it does not elaborate on side effects of resetState beyond the schema.

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-loads the usage context and key behavioral caveats. Its phrasing is somewhat terse and awkward ("...sessions: retry"), but it avoids unnecessary text.

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 full parameter coverage, annotations, and no output schema, the description covers safety and execution boundaries reasonably well. It still omits key retry semantics, such as whether retrying creates a new task, updates the existing one, or how it interacts with resetState.

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 100%, so taskId, resetState, and project_path are already documented. The description reinforces project_path isolation but adds little parameter-level meaning beyond what the schema provides.

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 names the action as "retry" and clarifies that it stores task metadata only rather than executing an agent. However, it does not explicitly say what retrying a task means in terms of task creation/state, so the purpose remains somewhat vague despite the tool name.

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?

It gives a broad usage cue ("Use when tracking persistent work across Codex sessions") and an exclusion ("does not start or execute an agent"). It does not distinguish this from siblings such as task_create, task_update, or task_complete, leaving the agent to infer when retry is appropriate.

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