Skip to main content
Glama
Sign In

FirstSited

by com.firstsited
OverviewDiscussionsAdmin

Stack breakdown

stack_breakdown

Counts and shares, not a list: for the sites matching a filter, how many use each technology, grouped by kind (payments, analytics, hosting, cms...). Answers any question of the form 'how many', 'what share', or 'which X do sites using Y use' in one call, for example 'what payment providers do Ghost sites use'. Use this BEFORE find_sites or export_sites for those questions; exporting rows and counting them costs hundreds of lookups for the same answer. Same filters as find_sites. Counts one Explore slice and no site allowance.

Input Schema

NameRequiredDescriptionDefault
nearNoOnly sites near a place: a town or city, a postcode, or 'lat,lng', e.g. Bristol. Use with radius. Sites we could not place are left out.
sinceNoEarliest LAUNCH date, YYYY-MM-DD.
untilNoLatest LAUNCH date, YYYY-MM-DD. Inclusive of the whole day.
radiusNoHow far from near, e.g. 30mi or 50km (a bare number is km). From 5 to 248 miles (8 to 400 km).
countryNoCountry as an ISO 3166-1 alpha-2 code, e.g. GB. Names are accepted too. Country is an ESTIMATE with a confidence score, so see minCountryConfidence.
regionsNoOnly 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 are left out.
categoryNoProduct category of the SITES, e.g. ecommerce. Not a kind of technology; for that see technologyCategory.
keywordsNoWhole 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, up to ten words. Combines with every other filter, so 'Stripe sites that mention photogrammetry' is technology plus keywords. The same rule create_watch uses, so a word that filters here is the word a watch would fire on.
technologyNoTechnology name, exactly as returned by list_technologies, e.g. ghost. The sites using it are the population; it is left out of its own breakdown.
observedSinceNoEarliest date we first recorded the site, YYYY-MM-DD.
technologyCategoryNoOne kind of technology to report on, e.g. payments, analytics, cms, hosting. Leave unset for every kind. list_technologies shows each technology's kind under 'category'.
minCountryConfidenceNoLeast country confidence to accept, 0 to 1. Pass 0.6 when the country needs to be right rather than merely likely.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Adds cost/quota context the annotations do not carry: it consumes 'one Explore slice and no site allowance'. It also discloses the result shape (counts and shares grouped by kind) and the population rule (the filtered technology is excluded from its own breakdown). It does not cover auth/permission requirements, but with annotations present the bar is lower.

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 key distinction in the first clause and orders guidance before the cost note. Slightly dense, with the parenthetical kind list ('payments, analytics, hosting, cms...') that is partly redundant with technologyCategory, 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?

For a 12-parameter, zero-required aggregation tool with no output schema, the description supplies the output form, the cost model, sibling routing and filter equivalence. It does not explain the response's grouping/nesting layout in detail, which is the only material gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real value by stating 'Same filters as find_sites', letting an agent transfer known filter semantics, and by tying the count dimension to technologyCategory versus category. The example 'what payment providers do Ghost sites use' clarifies how technology and filters combine.

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 output shape ('counts and shares, not a list') and the resource (technologies used by sites matching a filter, grouped by kind). It explicitly contrasts itself with the list-shaped siblings find_sites and export_sites, so an agent can select it without opening 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 Guidelines5/5

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

Gives an explicit routing rule ('Use this BEFORE find_sites or export_sites for those questions') plus the cost rationale ('exporting rows and counting them costs hundreds of lookups'). It also supplies the question shapes it answers ('how many', 'what share', 'which X do sites using Y use') with a worked example, leaving little to infer.

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

All FirstSited toolsInspect
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