Skip to main content
Glama

Compare Web Captures

compare_web_captures
Idempotent

Compare before/after web captures or recorded browser scenarios to surface every artifact-level difference and alignment failure, flagging where evidence is incomplete.

Instructions

Compare passive web captures by providing before and after, each with the complete inspect_web_page normalized_result in inspection and an optional complete discover_webmcp_tools normalized_result in webmcp; or compare recorded scenarios by passing complete capture_browser_scenario normalized_result objects in before_scenario and after_scenario with an optional normalization policy. Use exactly one input group. Network comparison includes observed HTTP requests and WebSocket frame streams; same-URL connections are compared as an unordered collection of ordered streams, retaining connection counts without claiming stable identity between individual connections. Scenario comparison aligns exact step IDs, records deterministic literal normalization, and returns every artifact-level difference plus alignment failures inline. Missing or truncated evidence never proves equality.

Input Schema

NameRequiredDescriptionDefault
afterNoThe later or right-hand observation to compare.
beforeNoThe earlier or left-hand observation to compare.
normalizationNoExact-literal rules committed in the comparison result.
after_scenarioNoLater complete normalized_result from capture_browser_scenario.
before_scenarioNoEarlier complete normalized_result from capture_browser_scenario.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare safety traits (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the description must carry the semantic burden and does: it explains that same-URL WebSocket connections are compared as an unordered collection of ordered streams with counts retained but no stable identity claimed, that scenario comparison aligns exact step IDs and returns alignment failures inline, and that missing or truncated evidence never proves equality. The remaining gap is that it never explains the comparison result's shape (equal/differ verdict, difference listing), which matters given no output schema.

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?

Purpose and the input-group contract are front-loaded in the first sentence, with comparison semantics following. The prose is dense and clause-heavy (a single long first sentence) but every sentence conveys a distinct behavioral fact rather than restating the name.

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?

For a tool taking five deeply nested evidence objects with no output schema, the description covers input provenance, mode exclusivity, comparison semantics for both network and scenario modes, and the soundness caveat about incomplete evidence. The one meaningful omission is what the returned comparison object looks like (sections compared, difference format), which an agent would otherwise have to discover by calling it.

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 documents each of the five parameters, including the mutual exclusivity via dependentRequired and the example normalization rule. The description reinforces this by requiring 'complete' normalized_result objects and describing the normalization policy as an optional third element of the scenario group, but it adds little syntax-level meaning beyond the schema.

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 ('Compare passive web captures') and immediately enumerates the two supported evidence types and the exact producer tools that generate each input (inspect_web_page / discover_webmcp_tools normalized_result, capture_browser_scenario normalized_result). This lets an agent distinguish it from siblings like compare_process_captures or compare_web_screenshots without opening the schema.

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

Usage Guidelines4/5

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

It gives an explicit selection rule between the two modes ('Use exactly one input group') and pairs each mode with the source tool whose output must be supplied, which is strong when-to-use guidance. It stops short of naming an alternative comparison tool or stating exclusions, so it is clear context rather than a full routing statement.

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