Skip to main content
Glama

squirrelscan

by com.squirrelscan

Compare two audits

compare_audits
Read-only

Compare two completed audits of one website and get what changed. Defaults to the website's latest completed audit against the one before it; pass base/head run ids to compare any two. Each finding gets one of seven kinds: new, resolved, worsened, improved, unchanged (both audits published it), still_open (the evidence store says it is still there but the newer audit did not republish it), or not_crawled (the page was not visited, so the issue is neither fixed nor still broken). resolutionEvidence says what backed the resolved verdicts; when it is "none" nothing is reported as fixed. Score movement is broken down by category. A website with only one audit returns first_run with an empty finding list; an audit where nothing moved returns changed: false. Unchanged, still-open and not-crawled rows are omitted unless requested.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
baseNoOlder run id. Default: the completed run before head.
headNoNewer run id. Default: the website's latest completed run.
limitNoMax findings returned (default 100). Totals are never capped.
website_idYesWebsite id from list_websites or run_audit.
include_unchangedNoInclude unchanged findings.
include_still_openNoInclude still-open findings (present per the evidence store, not republished).
include_not_crawledNoInclude not-crawled findings.

TDQS

A4.7/5.0
Behavior5/5

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

The annotations only indicate read-only, non-destructive behavior, so the description carries the burden of explaining behavior. It thoroughly discloses the seven finding kinds, the meaning of resolutionEvidence, score movement breakdown, and edge cases like first_run and changed: false. This goes well beyond what annotations provide.

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 dense but each sentence adds unique useful information, and the core purpose is front-loaded in the first sentence. The later sentences unpack the seven categories, edge cases, and include flags in a logical order without fluff or redundancy.

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?

With no output schema, the description compensates by explaining what the response contains: changed findings, seven categories, resolutionEvidence semantics, score movement by category, first_run behavior, changed: false, and default omission of certain rows. This is complete enough for an agent to invoke the tool correctly and interpret its response.

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 3, but the description adds meaningful semantics beyond the schema: base defaults to the run before head, head defaults to the latest completed run, limit totals are never capped, and the include_* flags correspond to findings that are omitted by default. This enriches the parameter understanding without repeating the schema verbatim.

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 precise verb and object: "Compare two completed audits of one website and get what changed." It clearly distinguishes this tool from siblings like get_audit_status or list_audits by emphasizing comparison and delta reporting rather than status or enumeration.

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?

The description explains defaults (latest completed audit vs the one before it), how to override with base/head run ids, and behavior for edge cases such as a website with only one audit. It does not explicitly name alternatives or say when not to use the tool, but the usage context is clear and actionable.

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

All squirrelscan toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool maps to a distinct resource-action pair: websites, audits, issues, rules, credits, notifications, and account info are cleanly separated. Even the close pairs (delete_website vs delete_websites, get_rule vs list_rules) are clear singular/bulk or fetch-all vs fetch-one distinctions.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: add_, delete_, get_, list_, run_, comment_, send_, create_. The only outlier, whoami, is a conventional standalone command and does not break the overall predictability.

Tool Count4/5

At 20 tools, the surface is slightly heavy, but the count is justified by the wide domain coverage: audit lifecycle, issue tracking, rule catalog, billing/credits, notifications, and account management. Each tool appears to earn its place, and none feel redundant.

Completeness4/5

The core workflow is well covered: run an audit, poll it, fetch a report, compare audits, list and comment on issues, browse rules, and manage websites. Minor gaps exist—no cancel-audit tool, no update_website, and issues cannot be status-changed—but agents can work around these using the existing tools.

Resources