aiworkhub_task_codex_handoff

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

Annotations already declare readOnlyHint=true, but the description adds substantial beyond-schema context: no write-gate toggle, no mutation parameters, it never calls taskctl done/review/start/auto-pickup/add-card, never mutates queue or audit state, never launches agents, and writes remain default-off regardless of input values. That is exactly the behavioral disclosure an agent needs before trusting a read-only call.

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?

Front-loaded with the READ-ONLY tag and the core purpose, then grouped into a summary line and a contract paragraph. Efficient overall, though the second paragraph is somewhat repetitive in its enumeration of prohibitions (no mutation parameters / never mutates queue / writes default-off).

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?

An output schema exists, so the enumerated field list is value-add rather than a gap, and the read-only contract is thoroughly covered. What remains missing is parameter guidance and disambiguation from the markdown sibling, which matters given the size of the surrounding tool surface.

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 0% for both parameters, so the description carries the full burden. 'For each task waiting on Codex review' implies that omitting task_ids defaults to all waiting tasks, but the description never mentions task_ids or explains what batch_label is or how it affects the report. An agent must guess the semantics of half the input surface.

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+resource: a Codex-ready handoff report over review-queue tasks, and enumerates the exact contents (task_id, runner, allowed_writes, validation commands, risks, commit hygiene, scoped commands). This is far more than a restatement of the name. It does not differentiate from the close sibling aiworkhub_task_codex_handoff_markdown, which an agent could easily confuse it with.

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 scope phrase 'For each task waiting on Codex review' implies the trigger condition, and 'WITHOUT mutating the parent task queue' hints at the read-only use case. However, no alternative is named (notably the markdown variant) and there is no explicit when-not guidance. Usage is inferable rather than stated.

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