Skip to main content
Glama

Нишка – отворен слой

Институциите в един град

institutions_overview
Read-onlyIdempotent

Across a city's public institutions in Nishka's data: how many have each contact channel, how long ago they were checked, what awaits review, which rules' fees changed in the last 90 days, whether contact pages answer, and letter outcomes in buckets — distributions, never a ranking — plus the alphabetical list of institution ids for institution_record.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "city": "<city>"
    },
    "name": "institutions_overview"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityYesplovdiv, sofia, varna or burgas.

Output Schema

NameRequiredDescriptionDefault
overviewYes
citationsYesEvery source the result rests on. Cite url; give checkedOn or publishedOn.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the remaining burden is data semantics, and the description delivers: it declares the non-ranking/statistical nature of the output, the 90-day fee-change window, the 'how long ago checked' recency dimension, and the bucketing of letter outcomes. It stops short of stating cost, aggregation scope limits (e.g. whether every institution is included), or latency considerations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One long, dash-heavy sentence carries a lot of genuine information with little filler, but it is not skimmable and front-loading is weak: the reader must parse six comma-separated analytics before learning the key caveat 'never a ranking' and the institution_record hand-off. Splitting the metric list from the caveat/hand-off would materially improve it.

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?

With a full output schema, one fully documented enum parameter, and rich read-only annotations, the definition supplies more than the minimum an agent needs: it names the dimensions returned and warns that results are distributions rather than rankings. The only residual gap is not clarifying the population covered (all institutions in the city vs. a filtered subset) or whether counts are inclusive of every listed id.

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 coverage is 100% and the single city enum is fully documented in the schema, so the baseline of 3 applies. The description reinforces that the city scopes 'public institutions in Nishka's data', which adds a little meaning about the data source but no new syntax or filtering semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates concretely what the tool produces: contact-channel counts, recency of checks, pending review items, fee rule changes in 90 days, contact-page responsiveness, and letter outcome buckets, plus an alphabetical id list. This is a specific and recognizable aggregate-overview resource that is clearly distinct from institution_record (whose input it feeds) and from single-metric siblings like institution_responsiveness. It loses a point only because the purpose is delivered as a run-on enumeration rather than a leading statement of 'this is a per-city aggregate overview'.

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?

'distributions, never a ranking' plus 'the alphabetical list of institution ids for institution_record' gives a clear use context and an explicit hand-off to the per-institution detail tool. What is missing is any exclusion against the other distribution-ish siblings such as institution_responsiveness or plovdiv_changes, so an agent must infer which aggregate to pick.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources