Delegate backend work to Codex

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this can modify the workspace. The description adds the mode distinction (analyze/review read-only vs implement edits), which is useful behavioral context. However, it doesn't disclose side effects like parallel risk, workspace mutations beyond targeted files, or concurrency behavior that a destructive tool might warrant.

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, zero filler. The first sentence states purpose and scope; the second adds the crucial read-only vs. edit mode guidance. Every word earns its place.

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?

This is a delegation tool with 9 parameters and a destructiveHint, no output schema. The description explains purpose and mode but doesn't cover interaction with same-domain sibling tools or failure/partial-success behavior. Given the schema richly documents all 9 parameters and the description covers the core behavioral distinction (read-only vs edit), it's adequate but not comprehensive.

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% with detailed parameter descriptions, so baseline is 3. The description adds value by explaining the domain-appropriate use of the tool and the mode semantics (read-only vs edits), reinforcing the 'mode' parameter's behavioral meaning beyond its schema description. It complements rather than repeats the 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?

The description uses a specific verb ('Delegate') with a clear resource ('backend, API, database, auth, infrastructure, security, performance, or backend-test work to Codex'). It clearly distinguishes from siblings by listing the backend domains, and the closest sibling (delegate_frontend) is differentiated by the explicit domain list.

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 clear guidance on when to use this tool ('Delegate backend...work') and distinguishes read-only vs. editing modes ('Use analyze/review for read-only work and implement for edits'). It lacks explicit 'when NOT to use' exclusions or named alternatives beyond the domain itself, but the mode guidance is valuable context.

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