Skip to main content
Glama

CompletionKit

by com.completionkit

runs_update

Update a run

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
nameNo
tag_namesNo
dataset_idNo
max_tokensNoCap on generated tokens per row. Leave unset to use the provider client's default, which is what silently truncates long outputs and makes the judge score malformed JSON. Set it to whatever the prompt uses in production so the eval matches.
metric_idsNo
judge_modelNo
temperatureNoSampling temperature for generation, 0 to 1. Leave it unset, which is the default, and no temperature is sent at all, so the model applies its own. Most current frontier models refuse the parameter outright; set it only when you are targeting a model that honours it, such as anything served locally through Ollama. A refused value is re-sent without one and the run is flagged temperature_ignored.
output_columnNo
expected_columnNo
metric_group_idNoReplace the run's metrics with those belonging to this metric group. Ignored when metric_ids is also given.
judge_temperatureNoSampling temperature for the judge, 0 to 1. Defaults to 0 so re-judging the same output gives the same score. Raise it only to measure judge variance on purpose; any value above 0 makes the run's scores irreproducible.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / temperature / description
      Previous value: -"Sampling temperature for generation, 0 to 1. Defaults to the column default. Reasoning models ignore it and the run is flagged temperature_ignored."New value: +"Sampling temperature for generation, 0 to 1. Leave it unset, which is the default, and no temperature is sent at all, so the model applies its own. Most current frontier models refuse the parameter outright; set it only when you are targeting a model that honours it, such as anything served locally through Ollama. A refused value is re-sent without one and the run is flagged temperature_ignored."
  2. Changed3 schema fields changed
    • addedInput schema / properties / judge_temperature
      Added value: +{
+  "description": "Sampling temperature for the judge, 0 to 1. Defaults to 0 so re-judging the same output gives the same score. Raise it only to measure judge variance on purpose; any value above 0 makes the run's scores irreproducible.",
+  "type": "number"
+}
    • addedInput schema / properties / max_tokens
      Added value: +{
+  "description": "Cap on generated tokens per row. Leave unset to use the provider client's default, which is what silently truncates long outputs and makes the judge score malformed JSON. Set it to whatever the prompt uses in production so the eval matches.",
+  "type": "integer"
+}
    • addedInput schema / properties / temperature
      Added value: +{
+  "description": "Sampling temperature for generation, 0 to 1. Defaults to the column default. Reasoning models ignore it and the run is flagged temperature_ignored.",
+  "type": "number"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / metric_group_id
      Added value: +{
+  "description": "Replace the run's metrics with those belonging to this metric group. Ignored when metric_ids is also given.",
+  "type": "integer"
+}
  4. First observed

TDQS

D1.8/5.0
Behavior1/5

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

With no annotations, the description carries the full burden of behavioral disclosure, but 'Update a run' reveals nothing about side effects, permissions, reversibility, or what happens to the run's data. Although some parameter descriptions in the schema mention behaviors like temperature_ignored flag, the main description itself is silent.

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

Conciseness2/5

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

The description is extremely short ('Update a run'), which avoids verbosity but is under-specified. It simply restates the tool name without adding useful detail, so it is not effectively concise—it is just minimal.

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

Completeness1/5

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

Given the tool has 12 parameters, no output schema, and no annotations, the description is grossly inadequate. It fails to explain typical use cases, the effect of updating a run, or any operational context, making it nearly useless for an agent deciding whether and how to invoke the tool.

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

Parameters1/5

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

The description adds no meaning for any of the 12 parameters. Schema coverage is only 33%, so the description was expected to compensate for the undocumented parameters, but it provides zero parameter-related information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Update a run' clearly identifies the verb (update) and resource (run), but provides no scope or specifics about what 'update' entails. It does not distinguish from sibling tools like runs_rerun or runs_regrade, which also modify runs, leaving the agent unsure of the exact purpose.

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

Usage Guidelines2/5

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

The description gives no guidance on when to use this tool versus alternatives such as runs_regrade or runs_rerun. No context, prerequisites, or exclusions are provided, leaving the agent without direction for tool selection.

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

All CompletionKit toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3/5.0
Disambiguation5/5

Each tool targets a distinct resource and action, with clear separation across agreements, datasets, judges, metrics, prompts, runs, tags, and usage. Even similar tools like datasets_create vs datasets_create_from_url and runs_generate vs runs_rerun are explicitly differentiated in their descriptions.

Naming Consistency5/5

The overwhelming majority of tools follow a consistent plural_resource_action snake_case pattern (e.g., datasets_create, metrics_update, runs_retry_failures). The only slight deviation is promptfoo_import, but it is still descriptive and does not break the overall predictability.

Tool Count1/5

With 54 tools, the server far exceeds the 25+ threshold considered too many, and approaches the 50+ extreme mismatch level. Even for a broad LLM evaluation platform, this count is excessive and likely to overwhelm agents, making tool selection more error-prone.

Completeness4/5

The toolset provides full CRUD for core resources (datasets, metrics, prompts, runs, tags) plus lifecycle operations like publish, generate, regrade, and retry. It also includes cross-cutting utilities (usage, import, provider credentials). Minor gaps exist, such as no update/delete for agreements and no cross-run response search, but these are non-essential for the primary workflows.

Resources