Skip to main content
Glama
lcc (Local Context Compiler)

lcc (Local Context Compiler)

recall

Retrieve the exact text removed by transcript compaction using its pointer ID; the local stash is re-hashed on read to verify the output matches what was cut.

Instructions

Return a tool output that compact_transcript (rules_mode 'stashed') replaced with '[removed: N lines, S KB · lcc recall ]'. The bytes are re-hashed on read, so the text is exactly what was removed. Offline, local stash only.

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": {
      "id": "<id>"
    },
    "name": "recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe hex id from the pointer.
fileNoOptional absolute path of the file this output read. Adds on_disk: {state: unchanged|changed|missing|unreadable, compared_as: numbered|lines, lines_compared, lines_differ}; counts only, never the file's content.
linesNoOptional 1-based range 'a-b'.
ledgerNoOpt-in: append one line of counts for this recall (outcome, bytes, age since stashed; never the id, text or paths) to the local ledger. LCC_LEDGER=1 turns it on for every call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.0
    • addedInput schema / properties / file
      Added value: +{
      +  "description": "Optional absolute path of the file this output read. Adds on_disk: {state: unchanged|changed|missing|unreadable, compared_as: numbered|lines, lines_compared, lines_differ}; counts only, never the file's content.",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv1.3.0
    • addedInput schema / properties / ledger
      Added value: +{
      +  "default": false,
      +  "description": "Opt-in: append one line of counts for this recall (outcome, bytes, age since stashed; never the id, text or paths) to the local ledger. LCC_LEDGER=1 turns it on for every call.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses that bytes are re-hashed on read so the returned text is byte-exact, and that the operation is offline and reads only a local stash. It omits error behavior when an id is missing or evicted, and does not state whether the stash is consumed or retained after recall.

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

Conciseness5/5

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

Two short sentences with the trigger condition front-loaded and the integrity/offline caveat second. Every clause earns its place; nothing is repeated from the schema.

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?

For a read-back tool with no output schema and no annotations, the description covers what is returned (the exact removed text) and the integrity guarantee. Missing only failure modes for stale or unknown ids, which an agent would need to handle robustly.

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 100%, so the schema already documents id, file, lines, and ledger in detail, including the on_disk comparison semantics. The description only adds the link between the required id and the pointer string it came from, which is marginal beyond the schema baseline.

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

Purpose5/5

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

States a specific verb and resource ('Return a tool output that compact_transcript ... replaced') and quotes the exact pointer string the tool reverses, so an agent can identify the situation unambiguously. It also names the sibling compact_transcript and the rules_mode that creates the stash, which differentiates it from siblings without opening their schemas.

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?

Usage is strongly implied and nearly explicit: when an output has been replaced by the '[removed: N lines, S KB · lcc recall <id>]' pointer, call this to get it back. The 'Offline, local stash only' clause scopes the context in which it will work. It does not explicitly state when NOT to use it or contrast with explain/inspect, so it falls short of a 5.

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