task_assign

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

Annotations already declare a non-destructive write, but the description adds real value beyond them: it states the tool stores metadata only and does not start or execute an agent, and it explains per-project store isolation via project_path. It does not disclose that the unassign flag wipes all agent assignments, which is a notable omission for a mutation tool.

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 short sentences with no filler, and the negative constraint about not executing an agent lands early. The colon construction ("...Codex sessions: assign") reads awkwardly, but no sentence is wasted.

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?

For a 4-parameter write tool with no output schema, the description covers the non-obvious behavior an agent needs: metadata-only semantics, no execution side effect, and project-scoped isolation. The missing piece is the effect of unassign and whether repeated assignment is idempotent.

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 all four parameters are already documented with meaning. The description reinforces project_path isolation but adds no new semantics for taskId, agentIds, or the unassign flag beyond what the schema states. Baseline 3 applies.

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 verb "assign" is given but the object is never stated outright — an agent must infer from the schema that it assigns agent IDs to a task. The second clause ("Stores task metadata only; does not start or execute an agent") does clarify what the tool is not, which separates it from an execution-style sibling, but the core action is left implicit.

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?

"Use when tracking persistent work across Codex sessions" gives a usage context, but there is no guidance on when to choose this over task_update, task_create, or task_complete, all of which are adjacent metadata-writing siblings. The reader is left to infer the boundary.

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