catalog_describeFills a pending catalog row by extracting content, search terms, and date from a document, enabling archivists to complete missing metadata.
Fill one '⚠ to describe' catalog row: content, search terms, date from the document.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | ||
| file | Yes | ||
| content | Yes | ||
| catalog_file | Yes | ||
| search_terms | Yes |
Changes observed during successful MCP inspections.
v0.1.1Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "additionalProperties": {
- "type": "string"
- },
- "title": "Result",
- "type": "object"
- }
- },
- "required": [
- "result"
- ],
- "title": "catalog_describeOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-destructive write (readOnlyHint=false, destructiveHint=false). The description adds that it targets a single catalog row and lists the fields, but it doesn't clarify overwrite behavior, prerequisites, or whether the document must be read first. The annotations carry most of the safety profile.
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 no filler. It is efficient, though the terse '⚠ to describe' jargon slightly reduces immediate comprehension for an agent unfamiliar with the marker.
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 five-parameter write tool with no output schema and zero schema descriptions, the definition is thin. It omits how catalog_file and file are specified, what happens if the row already has a description, and how this tool fits with catalog_check or the plan_* siblings.
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 0%, so the description must compensate. It gives meaning to three of five parameters (content, search_terms, date) but leaves catalog_file and file completely unexplained, even though those identifiers are essential for targeting the correct row.
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 has a specific verb ('Fill') and resource ('catalog row') and names the fields involved. It doesn't explicitly differentiate from siblings like catalog_check or suggest_names, and the '⚠ to describe' marker is jargon that assumes prior context, but the core action is clear.
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?
The phrase 'Fill one ⚠ to describe catalog row' implies the tool is used for rows flagged as needing a description, but it never explains where that flag comes from or when not to use it. No alternatives are named, leaving the agent to infer the workflow from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.