Skip to main content
Glama
Sign In
fernandogarzaaa

chimeralang-mcp

by fernandogarzaaa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

chimera_csm

CALL FIRST on every message. Optimizes input, estimates token cost, proposes budget. Show proposal_text to user for approval. After approval: constrain response to max_output_tokens and use optimized_prompt as effective input.

Instructions

CALL FIRST on every message. Optimizes input, estimates token cost, proposes budget. Show proposal_text to user for approval. After approval: constrain response to max_output_tokens and use optimized_prompt as effective input.

Input Schema

NameRequiredDescriptionDefault
focusNoOptional task focus/query. Defaults to prompt when omitted.
modelNoModel for pricing. Default: claude-sonnet-4-6claude-sonnet-4-6
promptYesThe user's raw input text to optimize and cost-estimate.
messagesNoOptional conversation history [{role, content}] for full context token count.
algorithmNoOptimization algorithm. quantum = query-aware compression. classic = legacy rewrite-only compression.quantum
task_complexityNoControls output token estimate. auto=detect from prompt keywords. simple=brief factual answer, moderate=explanation/how-to, complex=code/build/design. Default: autoauto

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.4
    • addedInput schema / properties / messages / items
      Added value: +{
+  "properties": {
+    "content": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "array"
+        }
+      ],
+      "description": "Message text, or a list of content blocks ({type: text, text})."
+    },
+    "role": {
+      "description": "user | assistant | system",
+      "type": "string"
+    }
+  },
+  "required": [
+    "content"
+  ],
+  "type": "object"
+}
  2. First observedv0.8.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it does disclose the two-phase propose/approve flow plus the operative output fields (proposal_text, max_output_tokens, optimized_prompt) that drive downstream behavior. It does not mention auth needs, failure modes, or what happens if approval is declined, leaving some gaps.

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?

Four compact sentences, front-loaded with the imperative 'CALL FIRST,' and each sentence conveys actionable information about ordering, output, and post-approval behavior. No filler.

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?

No output schema exists, so the description responsibly names the key return fields (proposal_text, max_output_tokens, optimized_prompt) and explains how to use them. Combined with 100% schema coverage this is largely complete, though the absence of annotation coverage leaves error/permission behavior unaddressed.

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 both enums (algorithm, task_complexity) are already documented with defaults, so the schema does the heavy lifting. The description adds no parameter syntax or format detail beyond restating the max_output_tokens/optimized_prompt usage, which are outputs rather than inputs.

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 specific verbs and resources: 'Optimizes input, estimates token cost, proposes budget,' and identifies the tool as the mandatory entry point ('CALL FIRST on every message'). It distinguishes itself by role as the pipeline starter, though it never names or contrasts with overlapping siblings like chimera_optimize, chimera_cost_estimate, or chimera_constrain.

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?

'CALL FIRST on every message' is an explicit when-to-use directive, and the approval workflow ('Show proposal_text to user for approval. After approval: constrain response...') tells the agent the sequencing. It lacks any when-not guidance or named alternatives, so it stops short of full routing guidance.

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

Deploy Server

Other Tools