Zovo Citation Generator

Format a manual citation

format_manual_citation

Read-onlyIdempotent

Use this when the user wants a citation generator, a reference generator apa or a works cited generator for a source they type in that has no DOI or ISBN: a book, a journal article, a chapter or a web page. Give the record fields and the style, and get the formatted citation plus BibTeX, RIS and text reference-list files. Use it for a cite this for me request about an old book or a class reading. Do not use it when the user has a DOI or an ISBN, or for legal cases, patents or datasets.

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": {
      "record": "<record>"
    },
    "name": "format_manual_citation"
  }
}

Input Schema

Name	Required	Description
`style`	No	Citation style: apa7 (default), mla9, chicago_ad or chicago_nb.
`record`	Yes	The source you type by hand when it has no DOI or ISBN.
`keep_capitals`	No	Words to keep as written, matched case-insensitively, e.g. ["Studies", "London"].

Output Schema

Name	Required	Description	Default
`note`	Yes
`count`	Yes
`items`	Yes
`style`	Yes
`sources`	Yes
`resolved`	Yes
`downloads`	Yes
`not_found`	Yes
`reference_order`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavior: it is manual-entry only (no identifier lookup), and it returns multiple output artifacts (formatted citation, BibTeX, RIS, text reference list), which matters for downstream use. It doesn't discuss validation failures for malformed hand-entered fields, but the annotation bar is already met.

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?

The trigger condition and the exclusion are front-loaded, which is good, but the text is padded with search-phrase paraphrases ('cite this for me', 'works cited generator', 'reference generator apa') that add words without adding meaning. It stays readable and short overall, so it's adequate rather than tight.

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

Completeness4/5

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

With a full input schema, an output schema, and complete annotations, the description covers the remaining gaps: manual-entry scope, supported source types, output artifacts, and explicit boundary cases. Only the relationship to the sibling generate_citations tool is left implicit.

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

Parameters3/5

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

Schema description coverage is 100%, so all record fields, the style enum and keep_capitals are already documented with examples. The description only restates 'give the record fields and the style' and repeats the supported type list already present in the enum, adding no new meaning such as style defaults or field requirements. Baseline 3 applies.

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

Purpose5/5

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

Specific verb (format) plus specific resource (a hand-typed citation record) and a stated input constraint (no DOI or ISBN). It also enumerates the supported source types (book, journal article, chapter, web page) and the deliverables (formatted citation plus BibTeX/RIS/text files), so an agent can distinguish it from a DOI/ISBN-driven generator without opening the schema.

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

Usage Guidelines4/5

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

It gives both a positive trigger ('user wants a citation generator ... for a source they type in that has no DOI or ISBN') and explicit exclusions ('Do not use it when the user has a DOI or an ISBN, or for legal cases, patents or datasets'). The only gap is that the excluded path is not tied by name to the sibling tool generate_citations, so the agent must infer the routing.

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

All Zovo Citation Generator tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?