Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

cachly_tool

Run any of cachly's specialist tools by name.

The most-used tools are listed separately above. This one reaches the other 98 without their schemas taking up room in every request.

When: compact_recover (after a context limit); brain_predict_failures (before a risky step, with odds); brain_plan (plan a task from past lessons); brain_conflicts (lessons contradict); memory_crystalize (condense lessons).

Unsure about a tool's arguments? Call it with describe:true first — that returns its input schema instead of running it.

Available: list_instances, create_instance, get_instance, get_connection_string, delete_instance, cache_delete, cache_exists, cache_ttl, cache_keys, cache_stats, detect_namespace, cache_warmup, cache_mset, cache_mget, cache_lock_acquire, cache_lock_release, get_api_status, recall_feedback, lesson_verified, session_start_summary, session_ping, auto_learn_session, brain_who_knows, brain_file_map, team_expertise_map, brain_collab_pairs, brain_portability, skill_gaps, brain_coverage, brain_metrics, brain_changelog, brain_service_map, sync_file_changes, team_confirm, team_assign_role, team_whoami, team_roster, team_audit, team_grant_scope, team_scopes, team_synthesize, memory_crystalize, team_crystallize, brain_hygiene, global_learn, global_recall, publish_lesson, import_public_brain, recall_at, trace_dependency, list_orgs, create_org, invite_member, get_org_plan, setup_ai_memory, cache_stream_set, cache_stream_get, cache_org_stats, set_cost_per_call, memory_consolidate, brain_diff, knowledge_decay, syndicate, syndicate_search, syndicate_stats, syndicate_trending, brain_marketplace, brain_install, ckg_inspect, brain_plan, brain_conflicts, brain_resolve_conflict, brain_confirm_ci, brain_briefing, brain_contribute_signal, brain_import_meta, madc_deliberate, cls_ingest, cls_install_hooks, fedbrain_contribute, fedbrain_search, fedbrain_confirm, fedbrain_status, brain_federate, crystal_view, compact_recover, brain_from_ci, brain_watch, brain_predict_failures, brain_share, brain_import, brain_share_list, brain_unshare, brain_discover, brain_seed_starter, brain_graph, brain_set_pref, brain_get_pref

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": {
      "tool": "<tool>"
    },
    "name": "cachly_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolYesName of the tool to run, e.g. "team_roster".
describeNoReturn the tool's input schema instead of running it.
argumentsNoArguments for that tool. Use describe:true if unsure.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does disclose the two behavioral modes: execute the named tool, or return that tool's input schema when describe:true. It also discloses the scope of dispatchable tools. It omits error behavior for an unknown tool name and whether results are passed through verbatim or wrapped.

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 opening sentence and the 'When:' block are front-loaded and earn their place, but the description ends with a 98-name dump that dominates the length and reads as a raw catalog rather than structured guidance. The list is functional for discovering valid tool names, but it is bulky and undifferentiated, so conciseness suffers.

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 and no annotations, so the description must cover behavior, and it does explain the schema-vs-execute fork. However, for a dispatcher over 98 tools it says nothing about what a successful invocation returns, how nested tool errors surface, or whether a name absent from the list is invalid. Adequate but with real gaps for a tool of this complexity.

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 100% and the schema already documents all three parameters, including the describe:true escape hatch and the note to use it when unsure. The description reinforces that workflow with an example ('e.g. "team_roster"') but adds no format or constraint detail beyond the schema. Baseline 3 is appropriate.

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: run any of cachly's specialist tools by name, and explains the mechanism (dispatcher for tools whose schemas would otherwise occupy every request). The distinction from the directly-exposed siblings is explicit in the sentence about the most-used tools being listed separately.

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?

Provides a concrete 'When:' list mapping five named tools to triggering situations (compact_recover after a context limit, brain_predict_failures before a risky step), which is real routing guidance. It also tells the agent to call describe:true when unsure of arguments. It does not state when not to use this wrapper versus a directly exposed tool, leaving that inference to the 'listed separately above' remark.

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.