Skip to main content
Glama

emem, the verifiable memory protocol for the physical world

Intent-routed planner

emem_intent
Idempotent

Say what you want in one typed object and get the answer, without choosing a primitive. type is a tagged union: it selects the intent AND decides which other fields are read, so send only the fields its row needs. The plan is EXECUTED in the same call, so you receive the result (the resolved cell64, the similarity, the delta, the verdict), not a list of calls to make yourself.

type | needs | optional | answers where_is | description | | cell64 for a named place what_is_here | cell OR place | description | what is attested at a location is_like | a, b | | cosine similarity of two cells did_change | cell, band, window | | delta for one band over [start,end] tslots find_like | key | k, filter | nearest cells by embedding confirm | claim, cell | | verdict plus the signed facts behind it ask | description | place/cell/lat+lng | free-text question, packaged answer

An unknown or missing type returns a structured needs_intent_type envelope naming the seven values rather than a hard error, so you can correct it on the next turn.

When to use: Call when the question maps onto one of the seven rows above and you would rather state the goal than pick a primitive. Otherwise go direct: a band at a cell is emem_recall, a region is emem_recall_polygon, a free-text place question is emem_ask (type:"ask" forwards to it). window takes tslots, not dates: get them from emem_trajectory. A tool named here but absent from tools/list is not a dead end: every one of the 114 dispatches by name at /mcp and /mcp/full; the core list is 18 to keep the catalog small, and emem_tools enumerates the rest.

Example arguments: {"type":"did_change","cell":"damO.zb000.xUti.zde78","band":"indices.ndvi","window":[20245,20620]}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
aNois_like only: cell64 of the first place in the pair.
bNois_like only: cell64 of the second place. The answer is a cosine similarity in [-1,1] over the two cells' embeddings.
kNofind_like only: how many neighbours to return. Defaults to the primitive's own default when omitted.
keyNofind_like only: cell64 to search from. Neighbours are ranked by embedding cosine against this cell.
latNoask only: latitude, paired with `lng`, when you want to pin the location by coordinate rather than by name or cell64.
lngNoask only: longitude, paired with `lat`.
bandNodid_change only: which band to test, e.g. "indices.ndvi". One band per call; the answer is a delta over `window`, not a whole-cell diff.
cellNocell64 address, e.g. "damO.zb000.xUti.zde78". Required by did_change and confirm. Optional for what_is_here and ask: supply it to skip geocoding, omit it and give `place` instead.
typeYesWhich question you are asking, and therefore which other fields apply. where_is: name a place, get its cell64 (needs `description`). what_is_here: summarise a location (needs `cell`, OR `place`/`description` to resolve it first). is_like: pairwise similarity (needs `a` and `b`). did_change: did one band move over a time window (needs `cell`, `band`, `window`). find_like: nearest neighbours to a known cell (needs `key`; optional `k`, `filter`). confirm: is a claim true at a cell (needs `claim` and `cell`). ask: free-text question about a place, runs locate + topic-route + recall server-side (needs `description`; optional `place`/`cell`/`lat`+`lng` to pin the location).
claimNoconfirm only: the claim to test at `cell`, e.g. {"band":"indices.ndvi","op":"gt","value":0.4}. The answer is a verdict plus the signed facts it rests on.
placeNoFree-text place name for what_is_here and ask when you have a name but no cell64, e.g. "Ashok Nagar, Ranchi". The responder geocodes it. Ignored when `cell` is present.
filterNofind_like only: optional claim constraining which cells may be returned. Same object as `claim` below, same ops, same required fields.
windowNodid_change only: exactly two tslots, [start, end], band-tempo-relative integers from the emem epoch (NOT unix seconds or a date string). Get valid tslots for a cell from emem_trajectory.
descriptionNowhere_is: the place to resolve, e.g. "Mount Everest". ask: the user's question, forwarded verbatim. what_is_here: optional free text used as the question and, if `place` is absent, as the place. Ignored by the other intents.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / claim / properties / value / type
      Added value: +[
      +  "string",
      +  "number",
      +  "boolean",
      +  "array",
      +  "null"
      +]
    • addedInput schema / properties / filter / properties / value / type
      Added value: +[
      +  "string",
      +  "number",
      +  "boolean",
      +  "array",
      +  "null"
      +]
  2. Changed5 schema fields changed
    • addedInput schema / properties / claim / properties
      Added value: +{
      +  "agg": {
      +    "description": "How a `window` reduces: any/all quantify over the facts in it; mean/min/max compare the reduced value against `value`.",
      +    "enum": [
      +      "any",
      +      "all",
      +      "mean",
      +      "min",
      +      "max"
      +    ],
      +    "type": "string"
      +  },
      +  "band": {
      +    "description": "Band to test, e.g. \"indices.ndvi\".",
      +    "type": "string"
      +  },
      +  "op": {
      +    "description": "Comparison. These ten spellings and no others: `greater_than`, `>` and `gte` are all rejected. in/ni take an array `value` (member / not member). exists and absent ask only whether the band is attested here.",
      +    "enum": [
      +      "eq",
      +      "ne",
      +      "lt",
      +      "le",
      +      "gt",
      +      "ge",
      +      "in",
      +      "ni",
      +      "exists",
      +      "absent"
      +    ],
      +    "type": "string"
      +  },
      +  "tslot": {
      +    "description": "Test at one tslot. Omit for the latest. Mutually exclusive with `window`.",
      +    "type": "integer"
      +  },
      +  "value": {
      +    "description": "Right-hand side. A number for the ordering ops, an array for in/ni. REQUIRED by the parser even for exists/absent, which then ignore it — omitting it fails the whole intent with `missing field value`."
      +  },
      +  "window": {
      +    "description": "Test across [start, end] tslots instead of one. Requires `agg` to say how the values across the window collapse to a verdict.",
      +    "items": {
      +      "type": "integer"
      +    },
      +    "maxItems": 2,
      +    "minItems": 2,
      +    "type": "array"
      +  }
      +}
    • addedInput schema / properties / claim / required
      Added value: +[
      +  "band",
      +  "op",
      +  "value"
      +]
    • changedInput schema / properties / filter / description
      Previous value: -"find_like only: optional claim constraining which cells may be returned, same shape as `claim`."New value: +"find_like only: optional claim constraining which cells may be returned. Same object as `claim` below, same ops, same required fields."
    • addedInput schema / properties / filter / properties
      Added value: +{
      +  "agg": {
      +    "description": "How a `window` reduces to a single verdict.",
      +    "enum": [
      +      "any",
      +      "all",
      +      "mean",
      +      "min",
      +      "max"
      +    ],
      +    "type": "string"
      +  },
      +  "band": {
      +    "description": "Band the neighbour must satisfy, e.g. \"indices.ndvi\".",
      +    "type": "string"
      +  },
      +  "op": {
      +    "description": "Comparison. Symbolic only: `gt`, not `greater_than` or `>`.",
      +    "enum": [
      +      "eq",
      +      "ne",
      +      "lt",
      +      "le",
      +      "gt",
      +      "ge",
      +      "in",
      +      "ni",
      +      "exists",
      +      "absent"
      +    ],
      +    "type": "string"
      +  },
      +  "tslot": {
      +    "description": "Test at one tslot. Mutually exclusive with `window`.",
      +    "type": "integer"
      +  },
      +  "value": {
      +    "description": "Right-hand side. Required by the parser even for exists/absent, which ignore it."
      +  },
      +  "window": {
      +    "description": "Test across [start, end] tslots instead of one. Requires `agg`.",
      +    "items": {
      +      "type": "integer"
      +    },
      +    "maxItems": 2,
      +    "minItems": 2,
      +    "type": "array"
      +  }
      +}
    • addedInput schema / properties / filter / required
      Added value: +[
      +  "band",
      +  "op",
      +  "value"
      +]
  3. Changed18 schema fields changed
    • addedInput schema / description
      Added value: +"A tagged union: `type` selects the intent and decides which OTHER fields are read. Fields belonging to a different intent are ignored, so send only the ones its row needs."
    • addedInput schema / properties / a / description
      Added value: +"is_like only: cell64 of the first place in the pair."
    • addedInput schema / properties / b / description
      Added value: +"is_like only: cell64 of the second place. The answer is a cosine similarity in [-1,1] over the two cells' embeddings."
    • addedInput schema / properties / band / description
      Added value: +"did_change only: which band to test, e.g. \"indices.ndvi\". One band per call; the answer is a delta over `window`, not a whole-cell diff."
    • addedInput schema / properties / cell / description
      Added value: +"cell64 address, e.g. \"damO.zb000.xUti.zde78\". Required by did_change and confirm. Optional for what_is_here and ask: supply it to skip geocoding, omit it and give `place` instead."
    • addedInput schema / properties / claim / description
      Added value: +"confirm only: the claim to test at `cell`, e.g. {\"band\":\"indices.ndvi\",\"op\":\"gt\",\"value\":0.4}. The answer is a verdict plus the signed facts it rests on."
    • addedInput schema / properties / description / description
      Added value: +"where_is: the place to resolve, e.g. \"Mount Everest\". ask: the user's question, forwarded verbatim. what_is_here: optional free text used as the question and, if `place` is absent, as the place. Ignored by the other intents."
    • addedInput schema / properties / filter
      Added value: +{
      +  "description": "find_like only: optional claim constraining which cells may be returned, same shape as `claim`.",
      +  "type": "object"
      +}
    • addedInput schema / properties / k / description
      Added value: +"find_like only: how many neighbours to return. Defaults to the primitive's own default when omitted."
    • addedInput schema / properties / k / minimum
      Added value: +1
    • addedInput schema / properties / key / description
      Added value: +"find_like only: cell64 to search from. Neighbours are ranked by embedding cosine against this cell."
    • addedInput schema / properties / lat
      Added value: +{
      +  "description": "ask only: latitude, paired with `lng`, when you want to pin the location by coordinate rather than by name or cell64.",
      +  "maximum": 90,
      +  "minimum": -90,
      +  "type": "number"
      +}
    • addedInput schema / properties / lng
      Added value: +{
      +  "description": "ask only: longitude, paired with `lat`.",
      +  "maximum": 180,
      +  "minimum": -180,
      +  "type": "number"
      +}
    • addedInput schema / properties / place
      Added value: +{
      +  "description": "Free-text place name for what_is_here and ask when you have a name but no cell64, e.g. \"Ashok Nagar, Ranchi\". The responder geocodes it. Ignored when `cell` is present.",
      +  "type": "string"
      +}
    • addedInput schema / properties / type / description
      Added value: +"Which question you are asking, and therefore which other fields apply. where_is: name a place, get its cell64 (needs `description`). what_is_here: summarise a location (needs `cell`, OR `place`/`description` to resolve it first). is_like: pairwise similarity (needs `a` and `b`). did_change: did one band move over a time window (needs `cell`, `band`, `window`). find_like: nearest neighbours to a known cell (needs `key`; optional `k`, `filter`). confirm: is a claim true at a cell (needs `claim` and `cell`). ask: free-text question about a place, runs locate + topic-route + recall server-side (needs `description`; optional `place`/`cell`/`lat`+`lng` to pin the location)."
    • addedInput schema / properties / window / description
      Added value: +"did_change only: exactly two tslots, [start, end], band-tempo-relative integers from the emem epoch (NOT unix seconds or a date string). Get valid tslots for a cell from emem_trajectory."
    • addedInput schema / properties / window / maxItems
      Added value: +2
    • addedInput schema / properties / window / minItems
      Added value: +2
  4. Added
  5. Removed
  6. First observed

TDQS

A4.9/5.0
Behavior5/5

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

While annotations already provide idempotentHint=true and destructiveHint=false, the description adds substantial behavioral detail beyond them: the tagged-union semantics, that the plan is executed in the same call, that fields belonging to another intent are ignored, and that an unknown or missing type returns a structured needs_intent_type envelope instead of a hard error. No contradiction with the annotations is present.

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

Conciseness5/5

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

The description is long but appropriately so for a 14-parameter tagged union with seven modes. It is front-loaded with the core concept, then organized into a compact table, a routing section, and an example. Every section contributes actionable information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description covers expected outputs per intent in the answers column, explains error-recovery behavior for invalid types, notes how to obtain valid tslots, and provides a runnable example. This is sufficient for an agent to select the tool and construct a correct call for any of the seven intents.

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?

The schema already provides 100% field coverage with detailed per-parameter descriptions, so the baseline is 3. The description adds value on top by mapping each type to its required versus optional fields, clarifying that only the fields 'its row needs' should be sent, and giving a concrete example. It does not substantially restructure what the schema already says, but it helps the agent navigate the union.

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?

The description states a clear purpose: 'Say what you want in one typed object and get the answer, without choosing a primitive.' It then enumerates seven distinct intents in a table, each with required fields and expected answers, making it easy to differentiate from sibling primitives like emem_recall and emem_ask.

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?

An explicit 'When to use' section gives both the positive condition ('Call when the question maps onto one of the seven rows above') and the negative routing with named alternatives ('Otherwise go direct: a band at a cell is emem_recall, a region is emem_recall_polygon, a free-text place question is emem_ask'). Additional guidance covers tslot semantics and how to handle tools not in the core list.

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.