List the user's short links with their valid view counts, most recent first. Useful to survey overall link performance or to find a code to dig into with link_stats.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max links to return (1-100, default 20). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It reveals the returned data includes valid view counts, that results are scoped to the user's links, and that they are ordered most recent first. This is sufficient for a simple read-only listing tool, though it does not describe edge cases like empty results or pagination.
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?
Two sentences, no filler. The first sentence states the core behavior and ordering; the second provides the use case and sibling linkage. The most important information is front-loaded and every sentence earns its place.
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?
For a low-complexity tool with one optional parameter and no output schema, the description is nearly complete: it covers scope, content, ordering, and intended use. A minor gap is that it does not describe the exact response shape, but the listing nature of the tool makes that less critical.
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?
The schema already fully documents the single limit parameter with range and default, so the description adds no parameter-level meaning. Baseline 3 applies because the schema coverage is 100% and the description doesn't need to compensate.
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?
The description uses a specific verb and resource: 'List the user's short links with their valid view counts, most recent first.' It clearly states what is returned and the ordering, and it distinguishes itself from sibling link_stats by framing list_links as the survey-level tool and link_stats as the per-code deep-dive tool.
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?
The second sentence gives actionable guidance: use this tool 'to survey overall link performance or to find a code to dig into with link_stats.' This implies the when-to-use and points to a sibling alternative. It does not explicitly mention shorten_url or exclusions, but the context is clear enough.
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 serves a clearly distinct purpose: creating a short link, listing links, and fetching stats for a specific link. There is no overlap or ambiguity between them.
Tool names follow a consistent verb_noun pattern: shorten_url, list_links, link_stats. All are lower_snake_case and uniformly readable.
Three tools is a reasonable, focused scope for a URL shortener server. It is slightly minimal but each tool covers a core need without unnecessary bloat.
The core URL shortening workflow is covered: create, list, and analyze performance. Missing update/delete capabilities are minor gaps since users can still manage links through the KooLink UI, but the tool surface has no obvious dead ends for its primary purpose.