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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds one genuinely useful behavioral fact — that the output comes from a deterministic algorithm engine rather than LLM generation, implying reproducibility — but says nothing about what happens when the optional counts are omitted or what the diagram output looks like.

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 compact statement with the resource name front-loaded in brackets, followed by the scenario and the return value. It is efficient, though the bracketed label partly duplicates the title and annotation title.

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 simple read-only generator with no output schema this covers the essentials — purpose, scenario, and return value. It is still incomplete on a practical point: all four parameters are optional, and the description never explains how the diagram is produced when counts are absent, which is the main ambiguity an agent faces.

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 100%, so each of the four parameters (title, records_identified, records_screened, studies_included) is already documented in Chinese in the schema. The description adds no parameter-level meaning, such as how counts map to PRISMA boxes or what defaults apply when a count is missing, so the baseline 3 applies.

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 states a specific resource and action — producing a PRISMA literature-screening flow diagram — and names the user context (systematic review / meta-analysis). It does not distinguish itself from the similar sibling act_consort_flow, which also generates a study flow diagram, so an agent must infer the difference from the names alone.

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?

Usage is implied by the phrase '用户做系统评价/Meta 分析，要画文献筛选流程图', which tells the agent the scenario that selects this tool. However, there is no explicit when-not guidance and no mention of the CONSORT-flow alternative for trial-style reporting, leaving the routing decision partly to inference.

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