Official PicSee MCP server for short links, link management, click analytics, and optional OAuth.
Scored across 1 tool
With only one tool exposed, there is no possibility of confusing it with another operation. Its purpose—creating a PicSee short link from a destination URL—is unambiguous and clearly stated.
The single tool uses a clean, predictable verb_noun snake_case convention (create_short_link). There are no competing styles to create inconsistency.
A single tool is a thin surface for a short-link service, which typically also involves listing, inspecting, or managing existing links. It covers the core creation action but feels minimal relative to the apparent domain.
Only link creation is supported; there is no way to retrieve, list, update, delete, or view analytics for existing short links. This leaves significant gaps for any workflow beyond one-off link generation.
Create a new PicSee short link from a destination URL. url is required; every other field is optional. Anonymous callers are pinned to the pse.is domain — any domain value supplied is ignored. The response contains picseeUrl, the shortened link ready to share.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Destination URL the short link should redirect to. Required. | |
| utm | No | UTM parameters appended to the destination URL. Pass `null` on edit to clear all previously set UTM values. | |
| domain | No | Domain to host the short link on (e.g. `pse.is` or one of the BSDs from `get_my_domains`). Falls back to the account default when omitted or invalid. | |
| encodeId | No | Custom slug (3-90 chars; English letters, digits, `_`, `-`, or Chinese). Must be globally unique on PicSee — conflicts return `PUB00503`. Omit to let PicSee auto-generate. | |
| externalId | No | Free-form identifier (1-100 chars) for grouping / attributing links. Surfaces in `list_short_links` filters and `get_api_usage_by_external_id`. When the user has not specified a value, you (the calling AI agent) SHOULD default this to your own product name so the account owner can attribute API usage back to the agent that created the link — e.g. `Claude Code`, `Codex`, `Cursor`, `ChatGPT`, `Gemini CLI`, `Copilot`. Use the canonical product name only; do not include version numbers or session IDs. If the user explicitly provides an `externalId`, always honor their value instead. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare a non-read-only, non-destructive, open-world write, and the description adds real context beyond them: the anonymous-caller domain pinning rule, the specific conflict error `PUB00503`, and the returned `picseeUrl` field. It stops short of covering rate limits or idempotency, but the auth-related nuance is genuinely useful.
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?
Three tight sentences, front-loaded with the required-input fact, then the auth caveat, then the return value. No filler or restated boilerplate.
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?
With no output schema, the description usefully names the returned `picseeUrl` field and covers required/optional params and anonymous-caller behavior. Minor gaps remain around error handling beyond slug conflicts and any rate-limit constraints.
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 coverage is 100%, so the baseline is 3, but the description adds behavior the schema does not: that `domain` is silently ignored for anonymous callers rather than honored or errored. That is a meaningful semantic addition for the highest-risk optional parameter.
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?
States a specific verb and resource ('Create a new PicSee short link') plus the source input ('from a destination URL'). No siblings exist to differentiate against, so nothing more is required for the agent to know what this tool produces.
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?
Clearly states that `url` is required and everything else is optional, and gives conditional context: anonymous callers are pinned to `pse.is` and any `domain` they pass is ignored. It lacks explicit when-to-use/when-not framing, but with no sibling tools there is nothing to route against.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
create_short_linkOfficial in.bio MCP server: shorten URLs, styled QR codes, and click analytics. No API key needed.
Official MCP server for POEditor, the translation management system. Hosted, OAuth 2.1.
The official Planning Center MCP server for interacting with your ministry's data.
Add one secure layer between your agents and this server.
