Skip to main content
Glama

MatLogica Demo

demo_replay_job

Queue the saved numerical recipe as a new calculation. It may reuse a retained kernel or record again; verify actual kernel/timing evidence. An admitted cache-policy-only release change carries explicit replay_source provenance.

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": {
      "job_id": "<job_id>",
      "idempotency_key": "<idempotency_key>",
      "guest_session": "<guest_session>"
    },
    "name": "demo_replay_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYes
guest_sessionYesWorkspace returned by demo_start_session in this conversation.
idempotency_keyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.3/5.0
Behavior3/5

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

Annotations already mark this as a non-read-only, non-destructive, closed-world operation. The description adds genuine behavioral context beyond that: the replay may reuse a retained kernel or recompute, and a cache-policy-only release change carries replay_source provenance — useful for an agent that must not assume determinism. However, it never states what is returned, how to follow the queued job, or what the idempotency_key actually guards, and the caching disclosure is phrased so cryptically that its practical value is reduced.

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 description is short and reasonably front-loaded with the action ('Queue ... as a new calculation'), so it is not bloated. But the brevity is spent on jargon-heavy clauses whose meaning an agent cannot act on, so the size is appropriate while the content is inefficient.

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

Completeness2/5

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

This is a mutating, three-required-parameter tool with no output schema and thin schema coverage. The description should explain what the queued result is, how replay differs from the original run in observable terms, and what idempotency_key protects; instead it delivers one vague caching caveat and leaves the rest of the calling contract implicit.

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

Parameters2/5

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

Schema description coverage is only 33% — only guest_session is documented. job_id and idempotency_key are conveyed solely through title and regex pattern, and the description does not compensate: 'saved numerical recipe' only obliquely implies job_id, and idempotency_key is never mentioned at all, leaving its retry/deduplication semantics unexplained.

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

Purpose2/5

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

The verb 'queue' is present, but the resource is described only in metaphor: 'the saved numerical recipe', 'retained kernel', 'record again'. The word 'job' never appears in the description even though the tool is demo_replay_job and its key parameter is job_id, so an agent must guess that the 'recipe' is the job. Nothing distinguishes this from siblings such as demo_get_job or demo_workbench.

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

Usage Guidelines2/5

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

There is no when-to-use statement, no preconditions (beyond the guest_session field), and no named alternative for inspecting versus re-running a job. The closest thing to guidance is 'verify actual kernel/timing evidence', which reads as an instruction about interpretation rather than about when to select this tool.

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