Modify an existing correspondent's name, matching pattern, or matching algorithm in Paperless-NGX to refine document auto-tagging rules.
Update an existing correspondent's name, matching pattern, or matching algorithm.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| name | Yes | ||
| match | No | ||
| matching_algorithm | No | Matching algorithm: 0=None, 1=Any word, 2=All words, 3=Exact match, 4=Regular expression, 5=Fuzzy word, 6=Automatic |
Changes observed during successful MCP inspections.
v2.2.1Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / matching_algorithm / descriptionAdded value: +"Matching algorithm: 0=None, 1=Any word, 2=All words, 3=Exact match, 4=Regular expression, 5=Fuzzy word, 6=Automatic"Input schema / properties / matching_algorithm / enumRemoved value: -[
- "any",
- "all",
- "exact",
- "regular expression",
- "fuzzy"
-]Input schema / properties / matching_algorithm / maximumAdded value: +6Input schema / properties / matching_algorithm / minimumAdded value: +0Input schema / properties / matching_algorithm / typePrevious value: -"string"New value: +"integer"v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It implies mutation and lightly signals that the target must already exist ('an existing correspondent'), but says nothing about permissions, whether fields are optional/partial, or reversibility of changes.
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 front-loaded sentence with zero filler. It is efficient, though extremely terse for a mutation tool with four parameters.
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 simple update tool with no output schema and no annotations, the description is minimally viable: the agent knows the resource and mutable fields. But with low schema coverage and no disclosure of return behavior or partial-update semantics, it stops short of full context.
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 only 25% (only matching_algorithm is documented in-schema). The description partly compensates by naming the updatable fields (name, match, matching_algorithm), but it leaves the required 'id' identifier and the 'match' pattern semantics unexplained, so it adds only marginal value.
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 (update) plus the resource (correspondent) and enumerates the mutable fields (name, matching pattern, matching algorithm). The intent is unmistakable, though it doesn't call out how it differs from siblings like bulk_edit_correspondents.
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?
No when-to-use guidance and no alternatives named. An agent must infer from the naming convention alone that bulk_edit_correspondents handles multiple records and that create_correspondent is the creation path.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.