workspace_decide_reference_expansion

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

No annotations are provided, so the description carries the full burden. It does disclose that execution is separate, which is helpful, but it does not explain side effects, persistence behavior, validation rules, idempotency, or what happens if a decision already exists.

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 sentence with no filler, and the core instruction is front-loaded. It is concise, though the terseness contributes to ambiguity.

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 a nested decision object, no output schema, no annotations, and many related siblings, the description is incomplete. It omits the meaning of run_id and edge_id, the allowed shape of decision, and what the tool returns, leaving significant gaps for an agent trying to call it correctly.

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%, and the description only partially compensates by mentioning candidate_id, target, existing_paper_id, skip:true, and retry:true. It does not explain run_id, edge_id, or how the decision object should be structured, so an agent still lacks enough meaning to build a valid request.

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 the verb 'Record' and lists decision-related fields, suggesting this tool records a decision about a reference expansion. However, it never explicitly names the resource ('reference expansion decision') and the field list is cryptic, so an agent cannot confidently distinguish it from create/update siblings without extra inference.

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?

'Advance separately to execute the approved choice' gives a useful hint that this tool only records and does not execute, implying a separate follow-up step. But it does not explicitly name the alternative sibling or state when not to use this tool, leaving usage conditions largely implicit.

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