Skip to main content
Glama

Calculer les metriques d'execution des agents

obs_metrics_summary

Aggregate logged events over a time window, returning volume, error rate, latency percentiles, tokens, cost, and top operations for AI agent monitoring.

Instructions

Agrege les evenements journalises sur une fenetre donnee : volume, nombre de traces, taux d'erreur, latences moyenne, p50, p95 et p99, tokens consommes, cout total et classement des cinq operations les plus appelees.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNoRestreindre a un type d'operation.
depuisNoDate ISO 8601 de debut de fenetre.
jusquaNoDate ISO 8601 de fin de fenetre.
projectNoRestreindre a un projet.
response_formatNoFormat de sortie. 'markdown' pour lecture humaine, 'json' pour traitement programmatique.markdown
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It describes aggregation but does not explicitly state read-only nature, performance implications, or any constraints. The verb 'Agrege' suggests read-only, but it is not definitive.

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?

A single efficiently constructed sentence that front-loads the primary action and enumerates the computed metrics. No redundant or extraneous content.

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?

With 5 fully described parameters and no output schema, the description compensates by listing key output metrics. However, it lacks details on response_format behavior or constraints like window limits, which would improve completeness.

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 description coverage is 100%, so parameters are well-documented. The description adds significant value by listing the output metrics (volume, error rate, latencies, etc.) that are not in the input schema, helping the agent understand what the tool computes.

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 description clearly states it aggregates logged events over a time window and lists specific metrics (volume, traces, error rate, latencies, tokens, cost, top operations). It distinguishes itself from sibling tools like obs_trace_get and obs_events_search, which are for individual traces or event queries.

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?

The description implies usage for aggregate metrics but does not explicitly state when to use this tool versus alternatives like obs_events_search or obs_anomaly_scan. No exclusion or prerequisite guidance is provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AgentIA1984-cmd/agent-observability-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server