Skip to main content
Glama

Estimate application cost

estimate_application_cost
Read-only

Estimate what a change to an Application would cost per month before making it. change is one of replicas, resources, park, promote, new_environment or database. replicas, resources, park and promote change an existing deployment and need its cluster_id and namespace; replicas needs replicas, resources needs cpu_request or memory_request. An answer with priced false names why in unpriced_reason and is not a cost of zero. Changes nothing.

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": {
      "application_id": "<application_id>",
      "change": "<change>"
    },
    "name": "estimate_application_cost"
  }
}

Input Schema

NameRequiredDescriptionDefault
changeYesThe kind of change to estimate.
serviceNodatabase only: the managed service engine; PostgreSQL when omitted.
replicasNoreplicas only: the new replica count.
namespaceNoThe namespace of the deployment the change applies to.
cluster_idNoThe cluster of the deployment the change applies to, or the cluster a new environment or database would run on.
parametersNodatabase only: the plan parameters, names to integers.
cpu_requestNoresources only: the new CPU request, as Kubernetes spells it (500m).
application_idYesThe Application's id.
memory_requestNoresources only: the new memory request, as Kubernetes spells it (512Mi).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and the description reinforces it with 'Changes nothing', then goes further by disclosing the failure mode: priced false surfaces a reason in unpriced_reason and must not be read as zero cost. That is a real behavioral warning the annotations cannot convey. What remains unstated is the shape of a successful priced response, which matters somewhat since there is no output schema.

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

Conciseness4/5

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

Front-loaded with the purpose, then the change-kind requirements, then the unpriced caveat and the read-only guarantee — a sensible ordering with no filler. It is telegraphic in places ('replicas needs replicas'), which costs a moment of parsing but keeps the definition short.

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 9-parameter tool with a nested object and no output schema, the description covers the conditional parameter rules and the one non-obvious response behavior (unpriced). It leaves the successful response's cost field and period implicit, which an agent would otherwise want spelled out, but nothing critical to correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter coordination the schema cannot express: replicas/resources/park/promote operate on an existing deployment and require cluster_id and namespace, while replicas needs replicas and resources needs cpu_request or memory_request. That conditional dependency map is genuinely useful. It does not explain the nested parameters object beyond the schema's 'names to integers'.

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 — estimating the per-month cost of a proposed change to an Application — and frames it as a preview before acting. The enumeration of change kinds and the closing 'Changes nothing' separate it cleanly from cost-reading siblings like get_object_cost and from mutation siblings like execute_cost_decision.

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?

Gives clear when-to-use context ('before making it') and tells the agent which parameter combinations each change kind requires, which is effectively routing guidance within the tool. It does not name an alternative tool for cases where a firm cost already exists, but the usage context itself is unambiguous.

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.