xTiles

xtiles_create_notification

Destructive

Create an in-app notification for the owner of the account you are working in, so they learn the work is done when they come back to it. It appears in their own notification feed inside xTiles: there is no recipient parameter and nothing is sent to anyone else. Call this AFTER you have finished all the work for the request, not before or mid-way. Call it once per place you touched (a project, or the Daily page), with one combined summary covering everything you did there — do not call it once per individual task/tile. If you touched two separate places, call this twice, once per place, each with its own url and summary.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	A ready-to-use absolute https URL on xtiles.app to the page where the work is visible (you build this URL yourself — the backend does not resolve a destination from ids). Must point at a page (e.g. the Daily planner for pure task creation, or the project/page you changed), not a specific tile. Example: https://xtiles.app/...
`text`	Yes	The notification's full display text. Compose it yourself: who (the agent), what it did, and where, with a count if it summarizes several changes in one place. One short sentence — the app shows at most 100 characters and cuts off the rest, and longer text is rejected. Examples: "Claude added 3 tasks to the \"Marketing\" project", "Claude updated \"Launch\" project: tile + 5 tasks".
`title`	No	Optional short headline shown above `text` in the phone notification: what happened, in a few words. At most 60 characters, one line. Do not put the agent's name here (the app already shows which agent sent it). Examples: "Daily Brief is ready", "Sprint plan updated".
`agent_source`	No	A raw label identifying the calling client, e.g. "Claude". Unrecognized values are accepted.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`sent`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 7, 2026

addedInput schema / properties / title

Added value: +{
+  "description": "Optional short headline shown above `text` in the phone notification: what happened, in a few words. At most 60 characters, one line. Do not put the agent's name here (the app already shows which agent sent it). Examples: \"Daily Brief is ready\", \"Sprint plan updated\".",
+  "maxLength": 60,
+  "type": "string"
+}

First observedOct 6, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Adds real behavioral context beyond annotations: no recipient parameter, nothing sent externally, and the 100-character display cutoff. However, the annotations declare destructiveHint=true and idempotentHint=false, and the description says nothing about why this benign-sounding notification is flagged destructive or what happens on repeated calls. It also omits any rate-limit or failure behavior. Useful additions, but the destructive/idempotency profile is left unaddressed.

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?

Front-loaded with purpose, then timing, then batching, all in short sentences with concrete examples. It is longer than strictly necessary — the final sentence about touching two places restates the preceding 'once per place' rule — but no sentence is wasted.

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?

An output schema exists, so return values need no explanation, and the batching/composition semantics are fully covered. The remaining gap is behavioral: no mention of the destructive flag, idempotency (duplicate notifications if called twice for the same place), or any limits, which is somewhat surprising given the annotations.

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 description coverage is 100%, so the schema already documents all four parameters with examples and length limits. The description adds the relevant clarification that there is no recipient parameter and that url/summary are keyed to a single 'place', but it largely restates what the schema carries. Baseline 3 is appropriate.

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?

States a specific verb and resource (create an in-app notification) and immediately scopes it: it targets the account owner's internal notification feed, not external recipients. No sibling tool competes for this role, and the description makes that distinct role explicit in the first sentence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives unambiguous timing ('AFTER you have finished all the work... not before or mid-way') and explicit batching rules: once per place touched, one combined summary, call twice if two places were touched. This is exactly the when/when-not guidance an agent needs and leaves nothing to inference.

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

All xTiles tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?