Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Read how the recorded posts performed

collect_post_metrics
Idempotent

Fetch and store performance metrics for recorded posts as a time-series, collecting due 24-hour and 7-day readings and skipping already taken ones. X skipped unless includeMetered; that costs credits.

Instructions

Fetch fresh performance numbers for this brand's recorded posts and store them as a time-series. Metrics ACCRUE, so a post is read at ~24 hours and again at ~7 days; this collects whichever readings are due and skips the ones already taken. A channel that cannot report a metric records it as ABSENT with the reason — never as zero — and a read that fails is recorded as 'could not tell', which contributes to nothing. X IS SKIPPED BY DEFAULT because X bills us per API call: pass includeMetered:true to include it, and tell the user it costs credits BEFORE you do. The skip is always reported so a channel missing from the numbers is never mistaken for one that performed badly. Free except for X.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxNocap how many posts to read in this run (default 40)
remeasureNoALSO re-read posts older than 7 days whose every reading came back empty or failed — use after post_performance reports posts "read but empty", or once a channel's reader has been fixed. Otherwise those windows stay closed.
includeMeteredNoalso read X, which BILLS CREDITS per post read — ask the user first

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.225
    • addedInput schema / properties / remeasure
      Added value: +{
+  "description": "ALSO re-read posts older than 7 days whose every reading came back empty or failed — use after post_performance reports posts \"read but empty\", or once a channel's reader has been fixed. Otherwise those windows stay closed.",
+  "type": "boolean"
+}
  2. Addedv0.1.161

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the safety/idempotency profile (readOnly false, idempotent true, destructive false), and the description adds substantial non-obvious behavior: metrics accrue at ~24h and ~7d, an unreportable metric is recorded as ABSENT with a reason rather than zero, failed reads become 'could not tell' that contributes to nothing, and X is skipped by default because it bills per call. It even explains that the skip is always reported to prevent misreading a missing channel as poor performance.

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 core action and organized from general behavior to edge cases to the metered exception. It is slightly long and leans on heavy capitalization for emphasis, but nearly every sentence carries distinct behavioral information rather than filler.

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?

For a mutating, write-to-time-series tool with no output schema, the description covers the traits an agent most needs: what gets written, how absent/failed reads are represented, idempotent skip behavior, and the cost gate on one channel. Nothing essential to calling it 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 a 3, but the description adds real meaning: includeMetered is tied to per-call billing and a user-consent requirement, and remeasure is explained as re-opening closed windows for empty/failed reads specifically after a reader fix. The max cap is left entirely to the schema, which is the only minor gap.

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 states a specific verb (fetch), resource (performance numbers for recorded posts), and side effect (store as a time-series), which is exactly what an agent needs to distinguish it from report-style siblings like post_performance or diagnose_posts. The 'this brand's recorded posts' scoping is precise and leaves no ambiguity about what is being collected.

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

Usage Guidelines5/5

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

Explicit when-to-use logic is given: collect whichever 24h/7d readings are due and skip the ones already taken, plus a named trigger for the alternative path ('use after post_performance reports posts read but empty'). It also states when X is included and the prerequisite of telling the user about credits first, so the routing decision is fully determined.

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