Retrieve source annotations and PMIDs for a previously queried or mapped interaction without fetching full-text papers or treating missing values as evidence.
读取此前查询/映射取得的来源注释和 PMID；不抓取论文全文，不把缺失值变成证据。
| Name | Required | Description | Default |
|---|---|---|---|
| interaction_id | Yes | ||
| max_references | No |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| error | No | ||
| status | Yes | ||
| coverage | Yes | ||
| warnings | No | ||
| provenance | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds genuinely non-derivable behavior: missing values are never promoted to evidence ('不把缺失值变成证据'), which warns the agent that sparse results are expected and should not be interpreted as findings. It does not disclose the max_references truncation behavior.
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?
A single compact sentence pair with the positive behavior front-loaded and the two exclusions trailing. No filler, and every clause carries distinct information.
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?
An output schema exists, so return values need no explanation, and the read-only profile is covered by annotations. However, with 0% parameter coverage the description should at minimum explain what interaction_id must be and that max_references bounds the reference list; those omissions leave real gaps for a two-parameter tool.
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 carries the full burden for both parameters — yet neither interaction_id nor max_references is mentioned. The agent gets no guidance on ID format, where interaction_id comes from, or that max_references caps citation retrieval (default 20, max 100).
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?
States a specific verb+resource: reads source annotations and PMIDs for an interaction, drawn from prior query/mapping results. It also carves out a scope boundary (no full-text retrieval), which separates it from search_interactions and download_official_file. The link to interaction_id is implied only via '此前查询/映射', so it is not fully self-contained.
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?
'此前查询/映射取得的' tells the agent this is a follow-up call after discovery, not a search entry point. '不抓取论文全文' explicitly rules out the full-text use case that would otherwise tempt an agent. No sibling tool is named as an alternative, so routing is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.