Save research evidence such as documents, static code, runtime observations, or interviews with a required source and limitation, so findings remain traceable and unverified claims stay marked.
保存研究者提供的资料、静态代码、运行观察或访谈记录。必须写明来源；工具不会把提交的文字当成已独立核验的事实。
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| title | Yes | ||
| source | Yes | ||
| content | Yes | ||
| study_id | Yes | 研究 ID，由 research_create 返回 | |
| limitation | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only tell the agent this is a non-destructive write (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description adds real behavioral context beyond them: the submission is stored as unverified input and is not promoted to an independently verified fact, which shapes how an agent should later reason about claims built on it. It still omits what the call returns and any permission or rate-limit constraints.
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 sentences: the first front-loads the action and accepted input types, the second states the source requirement and the trust caveat. No filler, no restatement of the tool name.
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 mutation tool with no output schema and almost no annotation detail, the description covers the trust model but leaves gaps: no indication of the persisted record's identity/return value, no mention of duplicate handling, study-state prerequisites, or how limitations are surfaced later. It is minimally viable rather than complete.
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 coverage is 17% — only study_id is documented — so five of six required parameters (title, kind, content, source, limitation) carry no schema explanation. The description implicitly maps the four kinds and stresses that source is mandatory, but says nothing about content vs. limitation semantics or the title field, so it only partially compensates 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?
The description gives a specific verb (保存/save) and resource (research materials, static code, runtime observations, interview records), matching the kind enum. It is clear what the tool does, but it never distinguishes itself from close siblings such as research_add_claim or research_add_verification, which also write evidence-like records to a study.
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 only implied: an agent can infer this is the entry point for ingesting raw source material, and the sentence '必须写明来源' sets a precondition on the source argument. There is no explicit when-to-use/when-not-to-use statement and no alternative tool named for the adjacent tasks (claims, verifications, node capture).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.