Skip to main content
Glama

inaturalist-mcp-server

Inaturalist Get Observation

inaturalist_get_observation
Read-onlyIdempotent

Fetch up to 10 observations by id with their community identification thread — who identified what, whether each identification agrees, and the consensus taxon the community landed on. The whole batch costs one upstream request, so resolving ten ids here is far cheaper than ten separate lookups. Records come back in the requested order. A missing id is reported per id in unresolved rather than failing the batch; the call fails only when nothing resolved. Long threads and long observation-field lists are cut to fit one response budget shared across the batch — up to 40 identifications, 40 comments, and 40 filled fields for a single id, 4 of each per record for ten — and every record reports the size of each array beside what it kept.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
includeNoEmbedded arrays to expand per record. identifications is the default and is what carries the thread; the others cost context, so check photo_count and sound_count first. identifications and comments — like the observation_fields every record carries — share a 40-entry budget across the batch: each record keeps at most 40 ÷ records returned entries per array (never fewer than 4), and reports identifications_total, comments_total, and observation_fields_total beside what it kept — request one id alone for the 40-entry view.
observation_idYesObservation ids to fetch, 1 to 10. Find current ids for an area with inaturalist_search_observations.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
noticeNoGuidance when part of the batch did not resolve, or when a thread or observation-field list was cut to fit the response.
unresolvedNoRequested ids upstream returned nothing for. They may have been deleted, or never existed.
observationsNoThe observations that resolved, in the requested order with unresolved ids left out, carrying the expansions that were requested.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changed
    • changedInput schema / properties / include / description
      Previous value: -"Embedded arrays to expand per record. identifications is the default and is what carries the thread; the others cost context, so check photo_count and sound_count first."New value: +"Embedded arrays to expand per record. identifications is the default and is what carries the thread; the others cost context, so check photo_count and sound_count first. identifications and comments — like the observation_fields every record carries — share a 40-entry budget across the batch: each record keeps at most 40 ÷ records returned entries per array (never fewer than 4), and reports identifications_total, comments_total, and observation_fields_total beside what it kept — request one id alone for the 40-entry view."
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when part of the batch did not resolve."New value: +"Guidance when part of the batch did not resolve, or when a thread or observation-field list was cut to fit the response."
    • changedOutput schema / properties / observations / description
      Previous value: -"The observations that resolved, with the expansions that were requested."New value: +"The observations that resolved, in the requested order with unresolved ids left out, carrying the expansions that were requested."
    • changedOutput schema / properties / observations / items / properties / agreements / description
      Previous value: -"How many identifications agree with the current taxon."New value: +"How many identifications currently agree with the community taxon."
    • changedOutput schema / properties / observations / items / properties / comments / description
      Previous value: -"Discussion comments. Present when \"comments\" was included."New value: +"Discussion comments, cut to their first entries in upstream order (not strictly chronological) when they exceed the per-record share of a 40-entry budget. Present when \"comments\" was included."
    • addedOutput schema / properties / observations / items / properties / comments_shown
      Added value: +{
      +  "description": "How many of them comments carries. Below comments_total when the thread was cut. Present when \"comments\" was included.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / observations / items / properties / comments_total
      Added value: +{
      +  "description": "How many comments upstream holds on the record. Present when \"comments\" was included.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / observations / items / properties / description
      Added value: +{
      +  "description": "The observer’s own note on the sighting — host plant, behaviour, habitat, count. Third-party free text. Present on the by-id tool; null when the observer wrote none.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / observations / items / properties / disagreements / description
      Previous value: -"How many identifications disagree with the current taxon."New value: +"How many identifications currently disagree with the community taxon."
    • changedOutput schema / properties / observations / items / properties / identifications / description
      Previous value: -"The identification thread. Present when \"identifications\" was included."New value: +"The identification thread, cut to its first entries in upstream order (roughly but not strictly chronological) when it exceeds the per-record share of a 40-entry budget. Present when \"identifications\" was included."
    • changedOutput schema / properties / observations / items / properties / identifications_count / description
      Previous value: -"How many identifications the thread holds."New value: +"Upstream’s tally of identifications currently agreeing or disagreeing with the community taxon — agreements + disagreements. Not the thread size: it leaves out the observer’s own identification and any that neither agrees nor disagrees, such as a coarser or withdrawn one. The thread size is identifications_total, on inaturalist_get_observation."
    • addedOutput schema / properties / observations / items / properties / identifications_shown
      Added value: +{
      +  "description": "How many of them identifications carries. Below identifications_total when the thread was cut. Present when \"identifications\" was included.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / observations / items / properties / identifications_total
      Added value: +{
      +  "description": "How many identifications upstream holds on the record — the thread size. Present when \"identifications\" was included.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / observations / items / properties / observation_fields
      Added value: +{
      +  "description": "Observation-field values filled in on the record, usually by a project; fields left blank are dropped. Cut to the first filled fields in upstream order when they exceed the per-record share of a 40-entry budget. Present on the by-id tool.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One filled observation field.",
      +    "properties": {
      +      "name": {
      +        "description": "Field name, as its creator wrote it, e.g. \"Habitat_Description\".",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "value": {
      +        "description": "The value filled in, verbatim.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "name",
      +      "value"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / observations / items / properties / observation_fields_shown
      Added value: +{
      +  "description": "How many of them observation_fields carries. Below observation_fields_total when the list was cut. Present on the by-id tool.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / observations / items / properties / observation_fields_total
      Added value: +{
      +  "description": "How many filled observation fields the record carries. Present on the by-id tool.",
      +  "type": "number"
      +}
  2. First observed

TDQS

A5/5.0
Behavior5/5

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

While annotations already mark this as readOnly/openWorld/idempotent, the description adds substantial behavioral detail: one upstream request per batch, results in requested order, per-id missing handling, the failure condition (only when nothing resolves), budget-based truncation (40/40/40 for one id, 4 each for ten), and size reporting for each truncated array. This is exactly the kind of context annotations cannot provide.

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 dense but every sentence earns its place. The main capability is front-loaded, followed by cost, failure semantics, and truncation behavior. No filler or repetition; the detail about missing ids and budget sharing is essential for correct invocation and interpretation.

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?

With an output schema present and only two parameters, the description covers all necessary runtime behaviors: batching, ordering, failure modes, truncation budgets, and per-record size reporting. There are no gaps an agent needs to call this tool correctly or interpret its results.

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

Parameters5/5

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

Though schema coverage is 100%, the description meaningfully extends both parameters. It explains the include default and what 'identifications' carries (the thread), warns that other includes cost context, and reveals the shared 40-entry budget mechanism. For observation_id it explains the 1-10 limit and points to the sibling search tool for finding current ids. The description adds real decision-making value beyond the schema.

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 opens with a specific verb+resource ('Fetch up to 10 observations by id') and states the key differentiator: it returns the community identification thread (who identified, agreement status, consensus taxon). This clearly separates it from search-based siblings like inaturalist_search_observations, which the description explicitly references for finding ids.

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?

The description gives explicit when-to-use context: batch resolution is cheaper than ten separate lookups, missing ids are handled per-id instead of failing the batch, and the batch fails only when nothing resolves. It also provides concrete selection guidance for the include parameter (check photo_count and sound_count first) and warns that large batches truncate thread data, recommending a single id for the full 40-entry view.

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.