workspace_advance_reference_expansion

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

With no annotations provided, the description carries the full burden. It discloses that the tool operates without per-paper prompts and within approved budgets, which is useful behavioral context. However, it does not explain what 'budgets' mean, whether it is idempotent, or what happens on partial failures. It doesn't contradict any annotations (since there are none), but it leaves significant behavioral unknowns for a complex workflow 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?

The description is a single, dense sentence that front-loads the core purpose ('Execute the saved policy') and includes key operational constraints (no per-paper prompts, within approved budgets, resume with run ID). It is concise and structured, though it could be slightly more organized with separate sentences for clarity.

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?

Given the complexity of the workflow (search, download, import, record) and the lack of output schema, the description provides a broad overview but misses critical details: What constitutes 'strong candidates'? How are budgets defined and enforced? What does 'record resolutions' mean? The tool has three parameters (one required) and no output schema, so the description should clarify the workflow's lifecycle, but it leaves many operational details ambiguous.

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 for the three parameters (run_id, max_steps, time_budget_seconds). The description mentions 'run ID' and 'budgets' but does not explain the meaning or format of any parameter in detail. For example, 'run_id' is mentioned as a resume key, but max_steps and time_budget_seconds are not elaborated. The description fails to fully clarify parameter semantics beyond what the schema provides (which is just names and types).

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 action (execute the saved policy) and the resource (reference expansion workflow), and lists the main steps (search, download arXiv sources, import candidates, record resolutions). It distinguishes from siblings like workspace_pause_reference_expansion or workspace_get_reference_expansion by focusing on the execution/resume action. However, it doesn't explicitly name an alternative tool for when to use a different tool, so it doesn't fully differentiate from all siblings.

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 mentions 'Resume with the same run ID,' which implies a prior run, but it doesn't explicitly state when to use this tool versus alternatives (e.g., when to use workspace_decide_reference_expansion or workspace_plan_external_imports_for_result). It provides context (resume with run ID) but lacks explicit exclusions or when-not-to-use guidance.

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