FirstSited

Create a watch

create_watch

Set up a standing watch that delivers newly discovered matching sites on a schedule. Narrow it by technology, keyword, category, country, region (a state or province), distance from a place or whether the site publishes a contact route; a completely unfiltered watch needs a plan that allows the every-site stream. Free to create, but delivered sites count against the monthly site allowance, and plans limit how many watches, technologies and keywords you may have. A webhook watch returns its signing secret exactly once when it is created.

Input Schema

Name	Required	Description
`near`	No	Only sites near a place: a town or city, a postcode, or 'lat,lng', e.g. Bristol. Use with radius. Sites we could not place never match.
`radius`	No	How far from near, e.g. 30mi or 50km (a bare number is km). From 5 to 248 miles (8 to 400 km).
`cadence`	No	How often to deliver: instant, hourly, daily or weekly. Email takes daily or weekly (default daily). Slack takes all four (default instant); hourly, daily and weekly post one grouped message per slot, and instant groups several matches arriving together. Webhook is always instant; portal stores the value but does not deliver.
`channel`	No	Delivery channel: email, webhook, slack, or portal for no outbound delivery. Default email.
`country`	No	Restrict to a country, ISO 3166-1 alpha-2 or a name. For several, use countries.
`regions`	No	Only sites in these states, provinces or other regions, e.g. ["Texas", "Oklahoma"]. Each a name, a name and country such as 'Georgia, US', or an id such as US-TX. A site matches if it is in ANY of them. Sites we could not place never match.
`category`	No	Restrict to a product category. For several, use categories.
`keywords`	No	Whole words to look for in a site's name, title or description, e.g. photogrammetry. Matches ANY of them; a multi-word entry is a phrase. Three characters or more. A common word is refused as too broad, with an estimate of what it would deliver. Combines with a technology: 'Stripe and photogrammetry' fits on every plan.
`countries`	No	Restrict to several countries, each an ISO 3166-1 alpha-2 code or a name, e.g. ["GB", "Ireland"]. A site matches if it is in ANY of them.
`categories`	No	Restrict to several product categories. A site matches if it is in ANY of them.
`webhookUrl`	No	Full HTTPS delivery URL, required for webhook or slack. It is stored encrypted; list_watches later returns only its host, never its path or query.
`technologies`	No	Technologies to watch, by name. A site matches if it uses ANY of them.
`hasContactPage`	No	Only sites that have a published contact page (true), or only those that do not (false). Omit for no filter; set both to require both. Needs the 'contacts' permission.
`hasContactEmail`	No	Only sites that have a published contact email (true), or only those that do not (false). Omit for no filter. Needs the 'contacts' permission.
`technologiesAll`	No	Also require ALL of these technologies.
`technologiesExcluding`	No	Exclude sites using any of these technologies.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 1, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds genuinely new behavior: creation is free but delivered sites count against the monthly allowance, plans cap watches/technologies/keywords, and a webhook watch returns its signing secret exactly once. That last point is critical and non-obvious.

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-loads the core action in the first sentence, then layers filters, cost/limits, and the webhook-secret caveat. It is dense but each clause carries information; only the long filter enumeration is slightly list-like.

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 a 16-parameter, all-optional creation tool with no output schema, the description covers cost implications, plan limits, and the one-time secret return, which is the key missing structured information. It does not describe the shape of the created watch in the response, a minor gap given there is no output schema.

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 every one of the 16 parameters is already documented. The description only broadly summarizes the filter axes (technology, keyword, category, country, region, distance, contact route) without adding syntax or interaction details beyond the schema, so baseline 3 applies.

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 ('Set up a standing watch') plus the outcome (delivers newly discovered matching sites on a schedule). It is clearly distinct from list_watches/delete_watch siblings without needing the schema.

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?

Gives concrete usage context: it lists the filter dimensions, notes that a fully unfiltered watch requires a plan allowing the every-site stream, and explains delivery channels. It does not explicitly name alternatives (e.g. find_sites for one-off searches) or state when not to create a watch, so it falls short of a 5.

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

All FirstSited tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?