PaperGraph MCP

workspace_get_dependency_reading

List main-result candidates or read a selected result with evidence, separating statement references from proof-local dependencies and flagging external references as reviewable plans.

Instructions

List main-result candidates or read a user-selected target with evidence.

Statement references and proof-local dependencies remain separate. External references produce reviewable plans only; empty evidence is not independence.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "paper_id": "<paper_id>"
    },
    "name": "workspace_get_dependency_reading"
  }
}

Input Schema

Name	Required	Default
`detail`	No	full
`paper_id`	Yes
`recursive`	No
`max_candidates`	No
`target_result_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.2.2Oct 17, 2026
- addedInput schema / properties / detail
```
Added value: +{
+  "default": "full",
+  "enum": [
+    "full",
+    "compact"
+  ],
+  "title": "Detail",
+  "type": "string"
+}
```
- addedInput schema / properties / max_candidates / maximum
```
Added value: +20
```
- addedInput schema / properties / max_candidates / minimum
```
Added value: +1
```
Addedv1.2.0Oct 2, 2026

TDQS

C2.4/5.0

Behavior2/5

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

With no annotations, the description carries the full burden, but it only offers abstract claims ('external references produce reviewable plans only; empty evidence is not independence'). It does not disclose side effects, permission/auth needs, or whether the operation is read-only, leaving the agent to infer safety behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and not padded, which is a plus. But the content is abstract and not front-loaded around the core action, so the brief text still leaves the agent parsing cryptic clauses rather than a clear directive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A five-parameter tool with 0% schema coverage, no annotations, no output schema, and a large set of closely-related siblings demands more than three abstract sentences. Key details an agent needs to invoke it correctly are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across five parameters, so the description must compensate. It only loosely hints at target_result_id ('user-selected target') and max_candidates ('candidates'); detail, recursive, and paper_id are entirely undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a dual capability (list main-result candidates or read a user-selected target with evidence), which roughly gives a verb+resource. However, terms like 'main-result candidates' and 'reading' are domain-jargon that don't clearly distinguish it from siblings like workspace_get_dependencies, workspace_get_result_reading_path, or workspace_get_evidence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use versus alternatives, and no prerequisites or routing logic. The 'Statement references and proof-local dependencies remain separate' sentence is a domain caveat, not usage guidance an agent can act on to choose this over a sibling.

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

Deploy Server