Skip to main content
Glama

Edit many entries live

update_entries
Destructive

Live edits to up to 25 entries in one request, each as update_entry_fields and update_entry_handles make one (the text fields, handles added and removed): a new revision each, audited with one batch id. Whether this key may edit each entry live is decided entry by entry, as for one edit (the dry run’s may_edit_live). By default each edit stands alone and the answer gives each one’s outcome; with atomic: true, any refused edit means none is made. Dry run by default: it reads each entry and lists what would change. The real run needs confirm set to the batch digest the dry run names. To ask a reviewer instead, use propose_entry_changes.

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": {
      "edits": "<edits>"
    },
    "name": "update_entries"
  }
}

Input Schema

NameRequiredDescriptionDefault
editsYesThe edits, each to a different entry.
atomicNotrue: all or nothing — if any edit is refused, none is made (the route answers 422 naming each refused edit). false (the default): each edit on its own.
confirmNoNeeded with dry_run: false: this change’s exact target, as the dry run gives it in `confirm`.
dry_runNotrue (the default): write nothing — show the change and the exact request it would send. false: make the change.
summaryNoWhy you made these edits, in a few plain words: each edit’s summary unless it gives its own. Shown in each entry’s public history. Never an internal tracking ID; a VHID is fine.
idempotency_keyNoOptional: a key you choose (1–255 printable ASCII, e.g. a UUID), sent as the write’s Idempotency-Key. Calling again with the same key and the same change within 24 hours answers the first call’s result (replayed: true) and writes nothing; the same key with another change is refused (422).

Output Schema

NameRequiredDescriptionDefault
noteNoA dry run: what to do next to make the change, in words.
resultNoA real run: the route’s own answer, where the tool adds facts of its own beside it.
confirmNoA dry run of a change that needs it: the exact target to send back as `confirm` with dry_run: false.
dry_runNotrue: a dry run, which wrote nothing. Absent from a real run.
replayedNoA real run with an idempotency_key already used for this change: the first call’s answer, given back; nothing was written now.
would_sendNoA dry run: the exact request the real run would send (`method`, `path`, any `headers` such as an Idempotency-Key, and its `body`, `form` or `query`), or the requests, in order.
may_edit_liveNoA dry run of a live edit: whether this key’s account may edit this entry live.
refused_becauseNoA dry run the real run would be refused for: why, in words.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / edits / items / properties / bio / description
      Previous value: -"A person’s date of birth (and optionally birth name and place of birth), each with the address of a source that states it, on an entry with NO Wikidata item; null removes it. The page states it like an item’s facts: for a person only, and only while they are 18 or over. Refused on an entry with a QID, where only the item’s facts are said; linking an item later drops it."New value: +"A person’s date of birth (and optionally birth name and place of birth), each with the address of a source that states it, on an entry with NO Wikidata item; null removes it. The page states it like an item’s facts: for a person only, and only while they are 18 or over. Refused on an entry with a QID, where only the item’s facts are said; linking an item later drops it. On an entry with no kind, saving them makes it a person, in the same revision."
    • addedInput schema / properties / edits / items / properties / native_name
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 200,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The entry’s name in its own script, shown under the title (e.g. 川瀬智子 for Tomoko Kawase); \"\" or null removes it and its language code. Plain text, at most 200 characters. Setting it takes it from the Wikidata sync, which otherwise fills it from the item’s name in native language (P1559)."
      +}
    • addedInput schema / properties / edits / items / properties / native_name_lang
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 35,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The language code of native_name, as Wikidata writes it (\"ja\", \"zh-hant\", \"ko\"); null for none."
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / edits / items / properties / bio
      Added value: +{
      +  "anyOf": [
      +    {
      +      "properties": {
      +        "birth_date": {
      +          "description": "The date of birth at the precision the source gives: \"2004-10-21\", \"2004-10\" or \"2004\".",
      +          "type": "string"
      +        },
      +        "birth_date_source": {
      +          "description": "The web address (http or https) of a source that states the date of birth.",
      +          "maxLength": 2048,
      +          "type": "string"
      +        },
      +        "birth_name": {
      +          "description": "The birth name, when the source gives one that is not the entry’s name.",
      +          "maxLength": 120,
      +          "type": "string"
      +        },
      +        "birth_name_source": {
      +          "description": "The address of a source that states the birth name (required with it).",
      +          "maxLength": 2048,
      +          "type": "string"
      +        },
      +        "birth_place": {
      +          "description": "The place of birth, as a reader would name it (\"Austin, Texas\").",
      +          "maxLength": 200,
      +          "type": "string"
      +        },
      +        "birth_place_source": {
      +          "description": "The address of a source that states the place of birth (required with it).",
      +          "maxLength": 2048,
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "birth_date",
      +        "birth_date_source"
      +      ],
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "A person’s date of birth (and optionally birth name and place of birth), each with the address of a source that states it, on an entry with NO Wikidata item; null removes it. The page states it like an item’s facts: for a person only, and only while they are 18 or over. Refused on an entry with a QID, where only the item’s facts are said; linking an item later drops it."
      +}
  3. Added

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing per-entry permission resolution (may_edit_live), that each edit yields its own new revision audited under one batch id, the atomic 422-on-refusal behavior, and the dry-run-first contract. It does not restate that writes are irreversible or how the idempotency_key replay window interacts with batching, which is left to the schema.

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

Conciseness4/5

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

Front-loaded and free of filler, with every sentence carrying a distinct operational fact. The phrasing is somewhat dense and elliptical in places ("each as update_entry_fields and update_entry_handles make one (the text fields, handles added and removed)"), costing a little first-read clarity.

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

Completeness5/5

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

For a destructive batch mutation with an output schema and full annotation coverage, this covers the pieces an agent would otherwise have to guess: scope, per-entry permission outcome, atomicity, dry-run default, the confirm handshake, and the reviewer alternative. Return values are rightly left to the output schema.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning to the workflow parameters: `confirm` is characterized as the batch digest the dry run returns rather than a vague 'exact target', and `atomic` is explained by its observable consequence (a 422 naming each refused edit). The `edits` cap of 25 and the per-entry nature are reinforced rather than merely repeated.

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?

Opens with a specific verb, resource, and scope: "Live edits to up to 25 entries in one request." It then pins the semantics of each item to the sibling single-entry tools ("each as update_entry_fields and update_entry_handles make one") and names the reviewer-facing alternative, so the agent can distinguish it from all three siblings without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit routing: use this for many entries at once, use propose_entry_changes to ask a reviewer instead, and dry run is the default unless confirm carries the batch digest. It also states when atomic should be preferred over the default per-edit outcome, with the exclusion that any refusal aborts everything.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.