task_create

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

Annotations already declare non-read-only, non-destructive, closed-world. The description adds genuine value beyond them: it stores metadata only with no agent execution, and writes are isolated per project_path so tasks don't leak across stores.

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?

Three short, front-loaded sentences with no filler. The sentence fragment 'create.' is slightly terse but the when-to-use clause leads, which is the right ordering.

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 6-param creation tool with full schema coverage and no output schema, the description covers trigger, side effects, and scoping adequately. It omits what the call returns (e.g., a task ID), which is a minor gap given no output schema exists.

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 every parameter is described in the schema, including the project_path isolation note. The description only reinforces the project_path scoping, adding little beyond structured fields, so 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?

States a specific verb (create) and resource (task) plus the persistence scope across Codex sessions. The clause 'stores task metadata only; does not start or execute an agent' sharpens what kind of creation this is, though no sibling (task_update, task_assign) is explicitly named.

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 clear trigger, and 'does not start or execute an agent' rules out a plausible misread. It stops short of naming alternatives like task_update or task_assign for related flows.

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