find_similarDetect near-duplicate documents by comparing text similarity, so new scans and re-downloads of the same file can be identified and reviewed.
Near-duplicates by text (new scan or re-download of the same document).
| Name | Required | Description | Default |
|---|---|---|---|
| area | No | ||
| paths | Yes | ||
| threshold | No |
Changes observed during successful MCP inspections.
v0.1.1Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "items": {
- "additionalProperties": true,
- "type": "object"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "find_similarOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered, but the description adds almost nothing beyond that: it does not say whether matching is fuzzy/similarity-based, what corpus is scanned, whether results are returned as groups or pairs, or anything about cost or limits. For a read tool with annotations this could have earned a 3 with one extra clause, but it supplies none.
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?
It is a single short fragment with no filler, so nothing is wasteful, but the terseness crosses into under-specification: the core claim is packed into a parenthetical rather than a front-loaded sentence stating what the tool does and on what inputs.
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?
With three parameters at 0% schema coverage, no output schema, and a closely related sibling (find_duplicates), the description leaves key questions unanswered: threshold semantics, area scoping, required paths, and how results are shaped. It is far short of what an agent needs to invoke this correctly.
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 and it does not. 'By text' slightly implies the comparison basis, but 'paths' (the only required parameter), 'area', and 'threshold' (default 0.8, clearly a similarity cutoff) are entirely unexplained — an agent cannot infer what a threshold of 0.8 means or what area scopes.
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 phrase 'Near-duplicates by text' does identify the resource being matched (near-duplicate documents) and the basis of matching (text content), with a parenthetical example. However, it is a noun fragment rather than a verb+resource statement, and it never contrasts itself with the sibling find_duplicates, so an agent cannot tell from the description alone which of the two duplicate-finding tools to pick.
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?
There is no explicit when-to-use guidance and no exclusions. The parenthetical '(new scan or re-download of the same document)' hints at a motivating scenario but does not say when to prefer this over find_duplicates or search, both of which appear in the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.