get_conflicts

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

With no annotations, the description carries the full behavioral burden. 『unresolved 保留雙版本』 hints that unresolved entries return both original and new values, which is useful, but it is ambiguous and says nothing about read-only safety, ordering, volume, or what a 'conflict' object is. Read-only behavior can only be guessed from the 'get_' prefix.

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 short clauses with no filler, and the resource is front-loaded. However, the brevity here is under-specification rather than efficiency — the space saved could have carried the run_id requirement or a hint about arbitrate_evidence.

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?

Placeholder

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 both parameters are undocumented in the schema. The description gestures at the unresolved concept (mapping loosely to only_unresolved) but never defines it or its default semantics, and the required run_id parameter is not mentioned at all. This does not compensate for the coverage gap.

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?

『衝突列表』 names the resource returned but supplies no verb and no scope (per-run? per-workspace?), so the agent must infer it retrieves conflicts. The second clause 『unresolved 保留雙版本』 is a cryptic behavioral remark rather than a purpose statement. It is distinguishable from siblings only because no other tool mentions conflicts.

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?

There is no statement of when to call this versus alternatives — most notably arbitrate_evidence, which is presumably the tool that resolves conflicts found here. No prerequisites, no mention that a run_id must come from a prior analysis job. Usage is left entirely to inference from the name.

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