Skip to main content
Glama

Model stats

model_stats
Read-only

A project's work by model over a period — the «By model» section of its stats screen. Per model ('model' one id, 'name', 'vendor', 'via' a router such as openmath, kept apart from the same model reached directly; 'built-in' is the tracker's own AI, named no further): 'issues' it worked on in the period or that closed in it, 'done' of those closed in it, 'now' at work at this moment, 'roles' and 'sources' (run, agent, manual) each with its count of issues, and 'runs' — the agent runs in the period that named this model alone, with what they reported: 'agentSeconds', 'inputTokens', 'outputTokens', 'cacheReadTokens', 'cacheWriteTokens', 'costUsd', each { value, runs }: a sum over the runs that reported it, value missing where none did — not reported, never zero. 'runs.shared' counts the runs this model shared with others; their numbers are in the top-level 'shared', added to no model. 'unnamed' is the runs that named no model. 'issues' and 'done' at the top count issues with any model. Issues are counted, never listed. The period is the last 30 days unless 'from'/'to' (YYYY-MM-DD, UTC) or 'days' say otherwise.

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": {
      "projectKey": "<projectKey>"
    },
    "name": "model_stats"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoThe last day, YYYY-MM-DD; today when left out.
daysNoHow many days back from 'to', when 'from' is not given (default 30, max 730).
fromNoThe first day, YYYY-MM-DD.
projectKeyYesThe project, e.g. 'PM'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover the read-only, closed-world profile, yet the description goes substantially further: shared runs are excluded from per-model sums and surfaced separately, 'unnamed' runs are called out, and metrics carry { value, runs } where a missing value means 'not reported, never zero'. It also makes clear issues are counted and never listed, which sets expectations about payload shape.

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?

The purpose is front-loaded in the first sentence and not a sentence is filler — every clause documents a returned field, which is necessary because no output schema exists. It loses a point for being a single dense paragraph mixing nested field definitions and period rules with no visual structure, making it harder to scan than it needs to be.

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

Completeness5/5

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

With no output schema, the description carries the full burden of explaining the return shape, and it does so thoroughly: top-level totals, per-model metrics, cost/token semantics, and the shared/unnamed buckets. Nothing an agent needs in order to interpret the result correctly 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 genuine meaning: it states the window is UTC (absent from the schema) and that the default is the last 30 days unless 'from'/'to' or 'days' say otherwise, clarifying precedence among the time parameters.

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?

The first sentence names a specific resource and scope: a project's per-model work statistics over a period, anchored to the «By model» section of the stats screen. An agent can tell instantly this returns usage/cost data broken down by model, and the following sentences enumerate exactly which fields come back.

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

Usage Guidelines3/5

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

Usage is implied by the subject matter (project model stats) and by the period rules, but there is no explicit statement of when to reach for this tool versus other stats or reporting tools, nor any when-not guidance. The agent must infer the appropriate call context from the purpose statement alone.

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