DEEPBOM

Inspect specific model evidence

deepbom_query_file

Read-onlyIdempotent

Use for follow-up questions about an already identified attachment: inspect a layer by subject_ref, search or page through all operations, inspect findings, rank improvement investigations, inspect encoded activation fusion, compare source-pinned static delegate eligibility, or explicitly analyze weight distributions, channels, similarity, singular spectra, sparsity and quantization with section=weights and optional weight_view. Weight analysis reads payloads on demand with explicit decoder/budget coverage (128 MiB widget limit). Reuse the ChatGPT-authorized file and the exact SHA-256 from its previous DEEPBOM result. section=profiles lists available backend profiles; query.target selects only a TFLite CPU planning profile from capabilities. The browser computes the query from the shared Evidence IR and returns a bounded result; model bytes are not sent to DEEPBOM. Static candidate eligibility is not observed placement, speed, accuracy, or runtime fusion. Do not invent findings while browser_query_started is pending.

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": {
      "file": "<file>",
      "expected_sha256": "<expected_sha256>",
      "query": "<query>"
    },
    "name": "deepbom_query_file"
  }
}

Input Schema

Name	Required	Description	Default
`file`	Yes
`query`	Yes
`analysis_depth`	No	Use structure unless the user explicitly asks to inspect serialized tensor payload values. Payload integrity can require reading the complete attachment.	structure
`expected_sha256`	Yes

Output Schema

Name	Required	Description	Default
`query`	Yes
`status`	Yes
`analysis_depth`	Yes	Use structure unless the user explicitly asks to inspect serialized tensor payload values. Payload integrity can require reading the complete attachment.	structure
`expected_sha256`	Yes
`analyzer_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 29, 2026

changedInput schema / properties / query / properties / section / enum

Previous value: -[
-  "operators",
-  "operator",
-  "findings",
-  "placement",
-  "fusion",
-  "improvements",
-  "profiles"
-]New value: +[
+  "operators",
+  "operator",
+  "findings",
+  "placement",
+  "fusion",
+  "improvements",
+  "profiles",
+  "weights"
+]

addedInput schema / properties / query / properties / weight_view

Added value: +{
+  "description": "Only for section=weights: explicitly opt into bounded payload analysis; use returned weight subject_ref to select a tensor. Default distribution.",
+  "enum": [
+    "distribution",
+    "channels",
+    "similarity",
+    "spectrum",
+    "sparsity",
+    "quantization"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / query / properties / section / enum

Previous value: -[
-  "operators",
-  "operator",
-  "findings",
-  "placement",
-  "fusion",
-  "improvements",
-  "profiles"
-]New value: +[
+  "operators",
+  "operator",
+  "findings",
+  "placement",
+  "fusion",
+  "improvements",
+  "profiles",
+  "weights"
+]

addedOutput schema / properties / query / properties / weight_view

Added value: +{
+  "description": "Only for section=weights: explicitly opt into bounded payload analysis; use returned weight subject_ref to select a tensor. Default distribution.",
+  "enum": [
+    "distribution",
+    "channels",
+    "similarity",
+    "spectrum",
+    "sparsity",
+    "quantization"
+  ],
+  "type": "string"
+}

AddedSep 29, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive/closed-world, but the description adds meaningful traits beyond them: payloads are read on demand under a 128 MiB widget limit, the browser computes the query and returns only a bounded result, model bytes are never sent to DEEPBOM, and 'static candidate eligibility is not observed placement, speed, accuracy, or runtime fusion'. The pending-state warning ('do not invent findings while browser_query_started is pending') is genuinely useful operational context.

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

Conciseness3/5

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

The core guidance is front-loaded, but the middle is a single sprawling sentence chaining eight 'or' clauses that mixes usage, parameters, and caveats together. It is information-dense but hard to parse, and some enumeration could be tightened without losing meaning.

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?

With an output schema present, return values need no explanation, and the description covers the important query modes, the payload/budget caveat, the meaning of static eligibility, and the dependency on a prior result. Only the analysis_depth dimension and explicit sibling routing remain unaddressed.

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 description coverage is only 25%, so the description carries real weight here and largely delivers: it explains section=weights with weight_view, section=profiles, query.target as a TFLite CPU planning profile (not detected hardware), and the file/SHA-256 reuse requirement. The notable gap is analysis_depth, which appears only in the schema and is not addressed in the 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?

The opening clause states a specific verb and scope: follow-up inspection of an already identified attachment, with the enumeration of sections (operators, findings, placement, fusion, weights, etc.) making the resource concrete. It implicitly distinguishes itself from deepbom_analyze_file via 'already identified attachment' and 'previous DEEPBOM result', but never names the sibling explicitly, so a 5 is not warranted.

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

Usage Guidelines4/5

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

It clearly routes the agent: use this for follow-up questions after an attachment has been identified, and reuse the ChatGPT-authorized file plus the exact SHA-256 from the prior result. There is no explicit 'when not to use' or named alternative tool, which keeps it below 5.

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

All DEEPBOM tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.