Skip to main content
Glama

workbench_read_record

Read-only

Reads stored analysis evidence as a compact summary, typed items, JSON Pointer field, or raw JSON, with location-grouped diagnostics and pagination via offset and limit for large records.

Instructions

Read evidence as a compact summary with location-grouped diagnostics, typed items, a JSON Pointer field, or complete original JSON text. Related records are grouped only by location, not assumed to share a root cause. Follow next_offset; sha256 always covers the complete stored record. Raw offsets count UTF-16 units; structured offsets count rows.

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": {
      "case_id": "<case_id>",
      "record_id": "<record_id>"
    },
    "name": "workbench_read_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNosummary
limitNo
fieldsNo
offsetNo
case_idYes
pointerNo
sectionNorecords
record_idYes
related_recordsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare read-only, non-destructive, open-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: related records are grouped only by location and not assumed to share a root cause, sha256 covers the complete stored record regardless of what was read, and next_offset drives pagination. These are real operational caveats beyond the structured fields.

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?

Front-loaded with what the tool returns before the caveats, and every sentence carries substance rather than filler. Density of jargon ("typed items", "location-grouped diagnostics") is high but appropriate for an expert agent audience; no wasted clauses.

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

Completeness3/5

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

There is no output schema, so the description is the only place return shape is conveyed, and it does name the output variants. For a 9-parameter read tool with zero schema coverage it is still too sparse, omitting what limit/fields/section/related_records do and how paging interacts with each view.

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?

Schema description coverage is 0% across 9 parameters, so the description must carry the load. It explains the view enum, the pointer (JSON Pointer) selector, and the tricky offset semantics (raw counts UTF-16 units, structured counts rows), which is valuable. But limit, fields, section (records/findings), and related_records receive no explanation at all, leaving nearly half the parameters undocumented.

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+resource ("Read evidence") and enumerates the output modes it can return: compact summary, location-grouped diagnostics, typed items, JSON Pointer field, or complete original JSON. An agent can tell what it retrieves, though no sibling tool is named as an alternative, so differentiation from the other workbench_* tools 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?

The description implies which view to pick by describing each output form, and gives one concrete usage instruction ("Follow next_offset"), but never states when to prefer raw vs summary vs field, or when to use this versus investigation/analyze siblings. Guidance is implied rather than explicit.

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