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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds one genuinely useful behavioral fact — the result comes from a real algorithm engine, not LLM generation — which tells the agent the output is deterministic and citable. It says nothing about what the returned checklist looks like beyond '条目核对', or whether a pass/fail verdict versus a gap list is produced.

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 compact clauses, front-loaded with the bracketed tool label, followed by trigger and return value. No filler, and the most useful distinguishing phrase ('真实算法引擎执行，非大模型生成') is preserved rather than padded away.

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?

For a zero-param, no-output-schema, read-only tool the description is nearly sufficient: it states the trigger and the return shape. The remaining gap is operational — how the study data reaches the tool and what a failing checklist looks like — which matters here because the agent can supply no arguments to steer it. It also lacks a fallback route to the sibling checklist tools.

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?

With zero parameters the baseline is 4, but this tool's zero-param design raises a real question the description ignores: nothing indicates where the experiment description to be checked comes from. An agent cannot tell whether it must first state the study details in the conversation or whether the tool reads prior context. That ambiguity costs a point despite the empty schema.

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 names a specific standard and action — checking an animal experiment against ARRIVE 2.0 and returning an item checklist. It distinguishes itself from the many statistical siblings by the ARRIVE/animal-research framing, though it never explicitly contrasts with the closest relatives act_checklist_check, act_consort_flow, or act_prisma_flow.

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?

It gives a concrete trigger condition: use when the user asks whether an animal experiment complies with ARRIVE 2.0. That is clear positive guidance. It stops short of exclusions — nothing says when to prefer act_checklist_check or what to do if the user asks about CONSORT/PRISMA instead.

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