Skip to main content
Glama

Organize with AI (OwAI)

Inspect duplicate sets

inspect_duplicates
Read-onlyIdempotent

Read one bounded page of complete duplicate sets for exactly one OwAI folder/source, matching the app's folder-scoped duplicate view. Every member includes its stable asset ID and filename. source_name or source_id from inspect_library identifies the folder. similarity_score is the lowest pairwise cosine similarity among a set's members.

Input Schema

NameRequiredDescriptionDefault
sortNomost_similar
limitNo
offsetNo
device_idNo
source_idNo
source_nameNo

Output Schema

NameRequiredDescriptionDefault
pageYes
sourceYes
duplicate_setsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed24 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / oneOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "source_name"
      +      ]
      +    },
      +    "required": [
      +      "source_id"
      +    ]
      +  },
      +  {
      +    "not": {
      +      "required": [
      +        "source_id"
      +      ]
      +    },
      +    "required": [
      +      "source_name"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / duplicate_sets / items / properties / asset_count / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / duplicate_sets / items / properties / asset_count / minimum
      Added value: +2
    • changedOutput schema / properties / duplicate_sets / items / properties / asset_count / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / duplicate_sets / items / properties / similarity_score / maximum
      Added value: +1
    • addedOutput schema / properties / duplicate_sets / items / properties / similarity_score / minimum
      Added value: +0
    • addedOutput schema / properties / page / properties / limit / exclusiveMinimum
      Added value: +0
    • addedOutput schema / properties / page / properties / limit / maximum
      Added value: +9007199254740991
    • changedOutput schema / properties / page / properties / limit / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / page / properties / next_offset / anyOf
      Added value: +[
      +  {
      +    "maximum": 9007199254740991,
      +    "minimum": 0,
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / page / properties / next_offset / type
      Removed value: -[
      -  "number",
      -  "null"
      -]
    • addedOutput schema / properties / page / properties / offset / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / page / properties / offset / minimum
      Added value: +0
    • changedOutput schema / properties / page / properties / offset / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / page / properties / returned / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / page / properties / returned / minimum
      Added value: +0
    • changedOutput schema / properties / page / properties / returned / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / page / properties / total_assets / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / page / properties / total_assets / minimum
      Added value: +0
    • changedOutput schema / properties / page / properties / total_assets / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / page / properties / total_sets / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / page / properties / total_sets / minimum
      Added value: +0
    • changedOutput schema / properties / page / properties / total_sets / type
      Previous value: -"number"New value: +"integer"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds real behavioral context beyond that: results are a single bounded page, each set is complete, every member carries a stable asset ID and filename, and similarity_score is defined as the lowest pairwise cosine similarity. It stops short of describing auth requirements or pagination interaction between limit and set count.

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?

Three dense sentences, well front-loaded with the core operation and scope before the identifier and similarity details. Nothing is wasted, though the final sentence about similarity_score sits oddly in an input-focused definition and could be tighter.

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?

An output schema exists, so return structure needn't be spelled out, and the description correctly avoids over-doing that. For a read-only, folder-scoped, paginated tool with an exclusive source_name/source_id constraint, the definition conveys the essential calling context; what remains missing is how pagination maps onto sets and the meaning of sort/device_id.

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?

With 0% schema description coverage, the description has to carry parameter meaning, and it partially does: it explains what source_name/source_id identify and that exactly one is used. It says nothing about sort ordering semantics, device_id, or how limit/offset page over sets, leaving four of six parameters unexplained in both schema and description.

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

Purpose4/5

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

States a specific verb and resource with scope: 'Read one bounded page of complete duplicate sets for exactly one OwAI folder/source'. It also references the sibling inspect_library as the source of the folder identifier, tying it into the tool graph. However, it never names resolve_duplicates, so the read-vs-mutate distinction from that sibling is left implicit.

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

Usage Guidelines3/5

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

It gives a prerequisite — source_name or source_id must come from inspect_library — which is genuinely useful flow context. But it offers no explicit when-to-use/when-not guidance or pointer to resolve_duplicates for actually acting on a set, so usage is only implied.

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.

Resources