Skip to main content
Glama

Agent Utilities Hosted

by dev.workers.agent-utilities.agent-utilities
OverviewDiscussionsAdmin

web_page_delta

Read-only

Return added and removed content blocks from supplied before/after HTML; avoid rereading unchanged text. Explicit shared output budget and scope. FREE during validation. No key, credits or wallet. Existing source and input limits apply.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputYes
requestIdNoOptional legacy field; ignored in free mode.
maxPriceMicroUsdNoOptional legacy field; ignored in free mode.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
addedYes
scopeYes
changedYes
removedYes
sourceUrlYes
truncatedYes
titleAfterYes
addedBlocksYes
measurementYes
titleBeforeYes
removedBlocksYes
reorderedOnlyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / maxPriceMicroUsd / description
      Previous value: -"Explicit maximum new debit; 0 means recovery only."New value: +"Optional legacy field; ignored in free mode."
    • removedInput schema / properties / maxPriceMicroUsd / maximum
      Removed value: -999999999999
    • changedInput schema / properties / requestId / description
      Previous value: -"Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty."New value: +"Optional legacy field; ignored in free mode."
    • removedInput schema / properties / requestId / pattern
      Removed value: -"^\\d{13}_[A-Za-z0-9_-]{16,80}$"
    • changedInput schema / required
      Previous value: -[
-  "input",
-  "requestId",
-  "maxPriceMicroUsd"
-]New value: +[
+  "input"
+]
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: FREE during validation, no key/credits/wallet, and that existing source and input limits apply.

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?

Compact and front-loaded: the core behavior leads, followed by the budget/scope and free-mode facts. Slightly telegraphic ("Explicit shared output budget and scope") but no wasted sentences.

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?

An output schema exists, so return values need no prose. Given the nested input, readOnly annotations, and output schema, the description covers the essentials (billing mode, limits, diff purpose); minor gaps remain around input size/format expectations.

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 67%; beforeHtml/afterHtml and maxChars carry no inline descriptions. The description hints that maxChars is a shared output budget and references scope, adding marginal meaning, but does not clarify the required before/after inputs beyond their names.

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

Purpose4/5

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

States a specific verb+resource: returning added/removed content blocks from supplied before/after HTML. An agent can distinguish this from data_json_diff or commerce_feed_page_compare by the HTML page-delta framing, though no sibling is named explicitly.

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?

"Avoid rereading unchanged text" implies the scenario (diffing two HTML captures to save re-reading), but there is no explicit when-to-use, when-not, or named alternative among the many diff/compare siblings. Usage is inferable but not guided.

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

All Agent Utilities Hosted toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources