Skip to main content
Glama
aston-cook

changelog

by aston-cook
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Grade logged changes

check_changes
Read-onlyIdempotent

Evaluate logged product changes and give a statistically honest verdict: moved, did not move, or cannot tell yet. Uses baseline data and detectability thresholds to avoid false conclusions.

Instructions

Return a verdict for each logged change: moved, did not move, or cannot tell yet. Computes the minimum detectable effect from the project's real baseline before reporting anything, excludes operator traffic at the person level, prefers the metric closest to the change over the revenue metric, and refuses to grade changes that overlap in time on the same metric. Returns "cannot tell yet" rather than "did not move" whenever the data could not have detected a meaningful change.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sinceNoOptional. Only grade changes logged on or after this instant. By default the whole log is graded, newest first — you do not need to pass this to reach older changes.
categoryNoOnly grade changes in this category.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

The description goes far beyond the readOnly/openWorld/idempotent annotations by disclosing the minimum detectable effect computation, operator-traffic exclusion, metric preference ordering, refusal of overlapping changes, and the 'cannot tell yet' safeguard. These are substantial behavioral traits an agent could not otherwise predict.

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?

The description is three dense sentences with the core purpose front-loaded. Every sentence adds a distinct behavioral rule or outcome, with no filler, tautology, or restatement of the tool's name.

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 read-only, idempotent grading tool with two optional fully-described parameters and no output schema, the description defines the verdict values and the key edge cases needed to interpret them. There are no obvious gaps in what an agent needs to invoke the tool correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already fully documents 'since' and 'category'. The description adds no parameter-specific semantics, but it is not required to compensate because the schema handles that burden.

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 opens with a specific verb and resource: 'Return a verdict for each logged change' and lists the exact outcome values. This clearly differentiates check_changes from the sibling log_change, which is about creating changes rather than grading them.

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 behavioral rules are clear, but there is no explicit statement about when to use this tool versus log_change or when not to use it. The choice between 'grade' and 'log' is implied rather than stated, so an agent must infer the appropriate usage context.

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