Skip to main content
Glama

Inspect Analysis View

inspect_analysis_view
Idempotent

Page through selected views of completed evidence—binary layout, JavaScript, native, inventory, WASM, EVM, managed, Android, Dart AOT, and captures—without rerunning analysis or reopening sources.

Instructions

Inspect selected views of completed binary-layout, JavaScript application, native analyze_function, inspect_artifact, inventory_artifact, inspect_wasm_artifact, inspect_evm_interface, inspect_managed_artifact, inspect_android_package, inspect_dart_aot or inspect_web_network_capture Evidence without repeating analysis. Historical capture summaries return identity and counts without bodies or archive inventories. Capture views page retained records: view {kind: "capture", detail: "preview" | "complete", offset: 0, limit: 20}; preview selects recorded headline fields and binary descriptors, complete returns exact records with all sidecars. Offsets follow the selected parent record order, preserving original producer ordinals. Paging never reopens the source or reruns the decoder. Qlog summaries keep profile/scope and counts; kind qlog pages traces, streams, loss-declarations, incomplete-records, contributions, ranges or final-sizes. Except traces, select trace_index; stream-specific facets also require exact stream_id and direction. Facts retain all-recorded-events-before-selection scope, and interval overlap or endpoint loss declarations do not prove retransmission or network loss. The api-surface view groups retained HAR requests by method, origin and format-rule path template; templated segments are inferences. It reads no headers or bodies and reports no query values. For a retained record use source: {kind: "retained-evidence", evidence_id: "<parent_evidence_id>"}. Use normalized_result.parent_evidence_id from a summary receipt. Source kind is required. Portable source uses {kind: "inline", evidence: }. For layout, JavaScript, inventory, WASM, EVM, managed artifact, Android package and Dart AOT sources, request a summary with view: {kind: "summary"}; summary is a view kind and has no facet. The WASM summary gives validation, counts, WAT digest/length, tool profile and execution/network states without reading WAT text. Select a layout mitigations/linkage facet, one section/symbol/module, or a stable page. Module pages include assets, bundled and source modules; use node_id for ambiguous or unavailable paths. Inventory uses view: {kind: "inventory", collection: "occurrences", logical_paths: ["package.json"], offset: 0, limit: 64}. Inventory views page nodes, occurrences, edges or integrity contradictions; occurrence logical_paths matches exact recorded strings (omitted means all available, [] means none). source_complete distinguishes complete inventories from partial source records; page exhaustion does not prove absence in a partial source. WASM views use kind wasm and facet sections/imports/exports/candidates/glue/wat/headers/details/tool_profile; text facets use UTF-16 code units and source forms remain exact. EVM summary returns all inferred interface candidates, carrier/decoded identities and explicit unknowns without hex or duplicate stdout. EVM views use kind evm and facet functions/bytecode_hex/stdout/stderr; function pages preserve the original candidate rows, and text offsets/limits count UTF-16 code units (hex has two characters per decoded byte). Exhausting candidate pages does not establish global interface completeness. Managed artifact summaries preserve complete identity/classification, metadata status, module/MVID, frameworks, coverage and limitations without unrelated inventories. Managed pages use kind managed and collection references/resources/attributes, retaining source coverage and build-local token scope; page exhaustion does not establish complete metadata. Android package summaries retain all declarations, engine identity and counts without decoded manifest text. Android manifest pages use kind android, facet manifest, offset and limit in UTF-16 code units; source_status preserves partial decoded coverage even when the retained text page is exhausted. Dart AOT summary preserves target/ABI/library identity, snapshot headers and pool lower bounds. String pages use kind dart-aot, collection package_uris/dart_uris/class_like_tokens; source coverage remains partial when the producer says partial. Native function Evidence requires kind native: view: {kind: "native", facet: "procedure"}. Facets select procedure, pseudocode, assembly, basic blocks, comments, callers/callees, references, unresolved calls, referenced strings/names, native API and high-pcode. Use nonnegative offset and a positive caller-selected limit (defaults 0 and 64); pseudocode uses UTF-16 code units, other native pages use rows. Returns artifact identity, parent Evidence ID, a distinct view digest, coverage, limitations and unknowns. Actual serialized size determines MCP transport admission; choose a smaller page or export the complete retained Evidence if needed.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "view": {
        "kind": "inventory",
        "limit": 32,
        "offset": 0,
        "collection": "occurrences",
        "logical_paths": [
          "package.json",
          "main.js"
        ]
      },
      "source": {
        "kind": "retained-evidence",
        "evidence_id": "ev_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
      }
    },
    "name": "inspect_analysis_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewYes
sourceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Goes well past the annotations (which only cover readOnly/destructive/idempotent) by disclosing epistemic behavior: page exhaustion does not prove absence in partial sources, interval overlaps and loss declarations do not prove retransmission or network loss, templated api-surface paths are inferences, and EVM candidate exhaustion does not establish global interface completeness. It also discloses transport admission being governed by actual serialized size and that offsets preserve original producer ordinals. There is mild tension between 'inspect' / 'never reruns the decoder' and readOnlyHint=false, but the description's note that it returns a distinct view digest is consistent with a new record being produced, so this is not a contradiction.

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

Conciseness2/5

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

A single ~500-word run-on paragraph with no sub-structure for what is effectively a 20-variant union; the malformed first sentence is not front-loaded and the essential routing facts (source kind required, use the parent evidence id, request summary first) are buried mid-paragraph. Useful rules such as 'page exhaustion does not prove absence' and 'text facets use UTF-16 code units' are restated per artifact kind, which adds length that could be stated once as a general rule.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool of this complexity with no output schema, the description covers what is needed: source shapes (retained-evidence vs inline), view shapes per artifact family, paging and unit semantics, and an explicit statement of what is returned (artifact identity, parent Evidence ID, distinct view digest, coverage, limitations, unknowns). An agent could construct a valid call and interpret partial coverage from this text alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Top-level schema description coverage is 0% over two required params (source, view) that resolve into a large union, so the description must carry the load and largely does: it enumerates view kinds (capture, qlog, inventory, wasm, evm, managed, android, dart-aot, api-surface, native, summary, item, page), which fields each requires, defaults (offset 0, limit 20/64/50), that logical_paths omitted means all and [] means none, and that offsets/limits count UTF-16 code units for text facets versus rows for native pages.

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 states a specific verb and resource — inspect selected views of completed Evidence — and adds the key differentiator 'without repeating analysis,' reinforced later by 'Paging never reopens the source or reruns the decoder.' The first sentence is garbled, though: it splices sibling tool names (analyze_function, inspect_artifact, inspect_wasm_artifact) into what reads as a list of artifact/Evidence types, which can leave an agent unsure whether those are source kinds or tools to call first.

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?

Gives concrete workflow guidance: source kind is required, retained evidence uses normalized_result.parent_evidence_id from a summary receipt, and layout/JS/inventory/WASM/EVM/managed/Android/Dart sources should first request view {kind: "summary"}. It also tells the agent what to do when a page is too large (smaller page or export complete Evidence). It never explicitly states when to use this tool instead of the sibling analysis tools, only that it does not re-run analysis.

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

Deploy Server

Other Tools