Skip to main content
Glama
Sign In

Layrcake

by dev.layrcake.mcp
OverviewDiscussionsAdmin

List replies

get_replies
Read-onlyIdempotent

Read campaign replies (free): newest first, optionally filtered by campaign_id and/or since (ISO timestamp). classification is out_of_office for an automatic reply and other for every other reply; it does not judge interest, so read the reply with get_reply and record what it meant with set_lead_status. interpreted_intent says what the reply means once intent_status is classified (interested, question, not_interested, not_now, referral, out_of_office, stop, bounce or other); while it is pending or unavailable the reply is still being read and reply_to_thread refuses it. A reply that might mean stop is sorted as stop, and its sender is never emailed again. classification stays the provider's.

Input Schema

NameRequiredDescriptionDefault
limitNo
sinceNo
campaign_idNo
idempotency_keyNoA payment_required refusal means services are stopped for unpaid billing; direct the owner to the billing link in the error. Campaigns stay paused after payment until restarted. Optional for search and enrichment tools: supply one so a retry returns the original result without paying again; if that call failed with provider_unavailable, rate_limited or insufficient_credits (after a top-up), a retry runs it once more after its cooldown (30 s, or a longer retry_after_seconds; insufficient_credits as soon as the balance covers it), unless its provider may already have done the work. Required for tools that create an external side effect; reuse the same value after a timeout or an approval. A stored failure comes back with details.replayed: true; with retry_after_seconds, retry the same value after that.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional for search and enrichment tools: supply one so a retry returns the original result without paying again; if that call failed with provider_unavailable, rate_limited or insufficient_credits (after a top-up), a retry runs it once more after its cooldown (30 s, or a longer retry_after_seconds; insufficient_credits as soon as the balance covers it), unless its provider may already have done the work. Required for tools that create an external side effect; reuse the same value after a timeout or an approval. A stored failure comes back with details.replayed: true; with retry_after_seconds, retry the same value after that."New value: +"A payment_required refusal means services are stopped for unpaid billing; direct the owner to the billing link in the error. Campaigns stay paused after payment until restarted. Optional for search and enrichment tools: supply one so a retry returns the original result without paying again; if that call failed with provider_unavailable, rate_limited or insufficient_credits (after a top-up), a retry runs it once more after its cooldown (30 s, or a longer retry_after_seconds; insufficient_credits as soon as the balance covers it), unless its provider may already have done the work. Required for tools that create an external side effect; reuse the same value after a timeout or an approval. A stored failure comes back with details.replayed: true; with retry_after_seconds, retry the same value after that."
  2. Changed1 schema field changed
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional for search and enrichment tools: supply one to make a retry replay the original result. Required for tools that create an external side effect; reuse the same value after a timeout or an approval."New value: +"Optional for search and enrichment tools: supply one so a retry returns the original result without paying again; if that call failed with provider_unavailable, rate_limited or insufficient_credits (after a top-up), a retry runs it once more after its cooldown (30 s, or a longer retry_after_seconds; insufficient_credits as soon as the balance covers it), unless its provider may already have done the work. Required for tools that create an external side effect; reuse the same value after a timeout or an approval. A stored failure comes back with details.replayed: true; with retry_after_seconds, retry the same value after that."
  3. Changed1 schema field changed
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Stable retry key; the same value identifies retries of the same request after timeout or approval."New value: +"Optional for search and enrichment tools: supply one to make a retry replay the original result. Required for tools that create an external side effect; reuse the same value after a timeout or an approval."
  4. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that: the call is "free", results are newest-first, and a stop-flagged reply's sender is never emailed again. But these are mixed with descriptions of output fields and other tools' behavior rather than this tool's own runtime traits.

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?

Purpose is front-loaded, but the description is long and conflates input filtering with output-field semantics (classification vs interpreted_intent, stop handling), which makes it denser than needed. Several clauses do not directly help an agent invoke this tool.

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?

There is no output schema, so the description carries the burden of explaining returns — and it does explain the classification and interpreted_intent fields and their relationship. Combined with the filtering and cost context, an agent has enough to call it correctly, though the unexplained limit parameter is a small gap.

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 coverage is only 25% (just idempotency_key), so the description should compensate. It clarifies since as an ISO timestamp and implies campaign_id is a filter, but omits limit entirely, and much of the prose describes output fields (classification, interpreted_intent) rather than the input parameters. Partial compensation, hence baseline 3.

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 resource ("Read campaign replies") plus ordering and optional filters, and it routes to distinct siblings (get_reply, set_lead_status, reply_to_thread). An agent can tell it apart from get_reply. However, the bulk of the text drifts into field semantics rather than reinforcing the core purpose.

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 explicitly tells the agent to read an individual reply with get_reply and record meaning with set_lead_status, and notes that reply_to_thread refuses replies whose intent is still pending. That is clear context, but it never states when NOT to use this listing tool or how it relates to find_leads/find_intent.

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

All Layrcake toolsInspect
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.

Resources