List Adaptation Tasks

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses useful internal behavior: the worklist is derived from the migration plan, uses the session overlay when built, and distinguishes shared_prompt_guidance from per-task guidance. However, it does not state whether the operation is read-only/idempotent, what side effects (if any) calling it produces, or any auth/precondition requirements beyond 'started migration run' — for an un-annotated tool this is a visible gap.

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 front-loaded well with the core purpose and call-once instruction, but the body is dense — the guidance-distribution detail, submission workflow, and finalize_migration routing are packed into long multi-clause sentences. It is informative but not easy to scan; the procedural detail could be tightened without losing meaning.

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?

The workflow is well contextualized: it describes what the worklist contains (prompt tasks with shared vs. per-task guidance, file tasks with the unchanged=true escape hatch) and how it fits between submit and finalize steps. Return shape is covered by the presence of an output schema, and the derivation semantics (session overlay) add useful depth. The main gap is the unexplained now parameter, which keeps this from a 5.

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%, so the description must compensate, but it explains neither parameter. run_dir is only weakly implied by 'a started migration run', and the now parameter (nullable string) is never mentioned at all — an agent cannot determine whether to pass it or what it controls. With 0% schema coverage and zero parameter explanation in the description, this is a clear shortfall.

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 clearly states the resource and action: a per-file adaptation worklist for a started migration run, with the front-loaded instruction to call it once. It distinguishes itself from the sibling submission tools (submit_adapted_prompt, submit_adapted_file) and finalize_migration by positioning itself as the listing step in the workflow. Minor gap: it never explicitly says it 'lists/returns tasks' — the noun 'worklist' implies it, but the primary verb is implied rather than stated.

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?

Provides explicit when-to-use context: call once at the start of adaptation, and explicitly states when NOT to re-list ('Submission results confirm acceptance, so re-listing between submissions is unnecessary'). It routes follow-up behavior to the right siblings — submit_adapted_prompt, submit_adapted_file with the unchanged=true option, and finalize_migration for remaining gaps. Strong procedural guidance, though it doesn't name an alternative listing tool explicitly.

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