Criora: climate & disaster risk for any place

Search Criora

search

Read-onlyIdempotent

Find Criora's documents to read and cite with fetch: a country's risk profile, a place's report, the methodology and data sources pages, and the data catalogue (climate layers, NDVI, country indicators). For an answer in one call the specific tools are shorter.

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": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	A country, a place, a subject (methodology, data sources, a layer such as flood depth, indicators) or a place and a subject: Miami sea level rise

Output Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 5, 2026
- removedOutput schema / $defs / SearchResult / properties / id / description
```
Removed value: -"What fetch takes: country:<ISO3>, place:<latitude>,<longitude> or page:<name>"
```
- removedOutput schema / $defs / SearchResult / properties / url / description
```
Removed value: -"The Criora page the result is about, for citing"
```

Changed9 schema fields changedNov 2, 2026

changedInput schema / properties / query / description

Previous value: -"A country, a place name, or a subject: methodology, data sources, or the data catalogue (layers, NDVI, satellite, indicators)"New value: +"A country, a place, a subject (methodology, data sources, a layer such as flood depth, indicators) or a place and a subject: Miami sea level rise"

removedInput schema / properties / query / title
```
Removed value: -"Query"
```
removedInput schema / title
```
Removed value: -"searchArguments"
```
removedOutput schema / $defs / SearchResult / properties / id / title
```
Removed value: -"Id"
```
removedOutput schema / $defs / SearchResult / properties / title / title
```
Removed value: -"Title"
```
removedOutput schema / $defs / SearchResult / properties / url / title
```
Removed value: -"Url"
```
removedOutput schema / $defs / SearchResult / title
```
Removed value: -"SearchResult"
```
removedOutput schema / properties / results / title
```
Removed value: -"Results"
```
removedOutput schema / title
```
Removed value: -"SearchResults"
```

Changed1 schema field changedOct 16, 2026

changedInput schema / properties / query / description

Previous value: -"A country, a place name, or a subject such as methodology or data sources"New value: +"A country, a place name, or a subject: methodology, data sources, or the data catalogue (layers, NDVI, satellite, indicators)"

AddedOct 13, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: results are documents intended to be opened with the fetch tool, i.e. this is a discovery step in a two-call workflow rather than an answer endpoint. It omits result-count, ranking and pagination behavior, which keeps it below a 5.

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?

Two sentences, front-loaded with the verb and the resource, and the document enumeration is efficient. The closing clause about specific tools is grammatically murky and costs clarity, but nothing is redundant enough to cut outright.

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?

This is a simple one-parameter read tool with an output schema, so return values need no explanation. The description covers what corpus is searchable and what the natural next step is (fetch). Only the ambiguity about which specific sibling replaces it for one-call answers leaves a gap.

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?

With a single parameter at 100% schema coverage, the schema already defines the query string with examples ('Miami sea level rise'). The description reinforces the accepted query shapes (a country, a place, a subject, or a place-plus-subject) but adds no syntax, matching or ranking rules the schema lacks. Baseline 3 applies since the schema carries the weight.

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 gives a concrete verb and resource ('Find Criora's documents to read and cite with fetch') and enumerates the document classes returned: country risk profiles, place reports, methodology and data sources pages, and the data catalogue with climate layers, NDVI and country indicators. That is far more specific than the bare name 'search'. It stops short of a crisp one-line differentiator from the many get_*/rank_* siblings, since it only gestures at 'the specific tools'.

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

Usage Guidelines3/5

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

There is a routing signal: use this tool when you want documents to read and cite, and use 'the specific tools' when you want an answer in one call. That is real when-to-use guidance, but it is compressed into a single awkward clause ('the specific tools are shorter'), names no sibling explicitly, and gives no when-not-to-use condition. An agent must infer which of the 20+ siblings to pick instead.

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

All Criora: climate & disaster risk for any place 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.