List the most recent CanaryUsers UX scans for your account (id, URL, CanaryScore, grade, status, date). Use this to find a scan to dig into.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many to return (default 10, max 50). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description bears the full burden. It discloses returned fields and account scoping, and 'List' implies a read-only operation. However, it does not mention ordering details (beyond 'most recent'), pagination behavior, or any permission requirements, which would add transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only two sentences and front-loaded with the main action. The parenthetical list of returned fields efficiently conveys output, and the second sentence adds a useful usage hint. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one optional parameter and no output schema. The description covers purpose, returned fields, and usage, which is sufficient for an agent to select and invoke the tool correctly. Minor omissions like exact sort order or pagination details do not significantly impair completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the only parameter 'limit', which is fully documented in the schema. The description adds no extra meaning beyond implying that the limit controls how many recent scans are returned, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action 'List' and the resource 'CanaryUsers UX scans', with the scope 'most recent' and the specific fields returned. This distinguishes it from siblings like 'canary_scan' (likely a single scan lookup) and 'get_report_markdown' (report retrieval).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states the use case: 'Use this to find a scan to dig into.' This provides clear context for when to invoke this tool. It does not name alternatives explicitly, but the purpose and sibling names imply the distinction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct role: canary_scan initiates a new scan, get_report_markdown retrieves a specific report, and list_recent_scans lists past scans. No overlap or ambiguity exists between them.
Two tools follow the verb_noun pattern (get_report_markdown, list_recent_scans), but canary_scan uses a noun_noun structure that doesn't explicitly indicate the action. The snake_case style is consistent, so the deviation is minor.
With only 3 tools, the server is tightly scoped to the core scan workflow: create, retrieve, and list. Every tool is necessary and sufficient for the service's purpose.
The tools cover the full lifecycle of a scan: initiate, fetch the report via scanId, and list historical scans. The workflow around asynchronous scan completion is fully supported with polling via get_report_markdown.
