Skip to main content
Glama
brunoboto96

SceneScout

by brunoboto96
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

scout_finding

Records structured UI test findings—bugs, UX issues, and improvements—with automatic deduplication, action-trace repro, and element/viewport screenshots for reporting.

Instructions

Record a structured finding (bug, UX issue, or improvement). Deduplicates across runs; automatically captures the recent action trace as the repro, and a picture of what it is about (the element ref names, else the viewport), kept for report.html and returned in this result as an image. Use for anything worth reporting: crashes, oracle violations you confirmed, dead ends, confusing UX, permission leaks, missing testids — and design-audit improvement opportunities (ux-polish) with their concrete measurements.

Input Schema

NameRequiredDescriptionDefault
refNoThe ref, from the latest scout_snapshot, of the element the finding is about. Its picture (the element plus a margin) is kept with the finding and shown in report.html. Omit it and the picture is the viewport.
titleYesOne-line summary of the defect
detailYesWhat happened, what was expected, and the evidence
sessionNoTarget this session directly instead of the active one — pass it explicitly when dispatching to MULTIPLE sessions in one turn (e.g. two scout_click calls with different `session`), which then run CONCURRENTLY rather than queueing. Omit for single-session sequential use.
categoryYesPick the closest — use 'other' only when nothing fits
evidenceNoCanonical machine signature for dedup, e.g. 'GET /api/reports/dashboard 403' or 'widget dashboard-summary-widget shows 0'. Same bug re-found later should produce the same string.
severityYes
conventionNoOnly for a WORTH-A-LOOK finding: the observation is real, and it is a defect only under a convention of this project you cannot see. Name that convention, e.g. 'a 4px spacing scale' or 'test ids on every control'. The report lists it under "Worth a look", apart from the defects, and does not count it as one. Not for "I could not tell": leave that unfiled or look closer. Omit for a defect.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.31.0
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Changed1 schema field changedv3.17.0
    • addedInput schema / properties / ref
      Added value: +{
+  "description": "The ref, from the latest scout_snapshot, of the element the finding is about. Its picture (the element plus a margin) is kept with the finding and shown in report.html. Omit it and the picture is the viewport.",
+  "maxLength": 20,
+  "type": "string"
+}
  3. Changed1 schema field changedv3.14.1
    • addedInput schema / properties / convention
      Added value: +{
+  "description": "Only for a WORTH-A-LOOK finding: the observation is real, and it is a defect only under a convention of this project you cannot see. Name that convention, e.g. 'a 4px spacing scale' or 'test ids on every control'. The report lists it under \"Worth a look\", apart from the defects, and does not count it as one. Not for \"I could not tell\": leave that unfiled or look closer. Omit for a defect.",
+  "maxLength": 160,
+  "minLength": 1,
+  "type": "string"
+}
  4. Addedv1.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses deduplication across runs, automatic capture of the action trace as repro, automatic element/viewport screenshotting, persistence into report.html, and return of that image. It does not state what happens on a duplicate hit (merged? returned id?) or permission/session prerequisites, which are the remaining behavioral gaps for a mutation tool.

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?

Effectively one dense paragraph of three sentences, front-loaded with the action and followed by purpose/behavior/examples in a sensible order. It is long but nearly every clause carries information; the parenthetical about report.html and the returned image is slightly buried mid-sentence.

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 an 8-parameter write tool with no output schema, the description covers purpose, side effects, storage, and return (image), which is most of what an agent needs. Missing are severity grading guidance and the outcome of deduplication, which matter for correct invocation but are secondary.

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 coverage is 88%, so baseline is 3 and the description adds little beyond it: ref semantics are restated, and category is only implied through examples. `severity` is required with an enum and no schema description, yet the description never says how to grade high/medium/low — a real omission the description could have filled.

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?

Opens with a specific verb+resource ('Record a structured finding') and immediately narrows the domain to bugs, UX issues, and improvements, then enumerates concrete qualifying cases (crashes, dead ends, missing testids, ux-polish). It is unmistakably a write-a-defect tool rather than a navigation or inspection tool, though it never names the nearest sibling (scout_note) to draw the line explicitly.

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?

'Use for anything worth reporting:' followed by a concrete enumeration gives clear positive selection criteria, and the convention field adds a genuine negative case ('Not for "I could not tell": leave that unfiled'). It lacks an explicit contrast with scout_note or scout_ticket_file, so the agent must infer when a finding becomes a ticket.

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