Atisbo

atisbo_capture

Destructive

Capture Signals or knowledge; update, patch or add evidence to artefacts.

Input Schema

TableJSON Schema

Name	Required	Description
`mode`	Yes	Capture mode. Mode-specific notes return in meta.guidance after the call.
`note`	No	Why it matters or ingestion context.
`text`	No	Signal text.
`items`	No	signal_batch, max 100.
`title`	No	Knowledge or evidence title.
`source`	No	Signal source. Defaults to manual.
`content`	No	Knowledge or artefact content.
`evidence`	No	Evidence fields; document_id is top-level.
`modality`	No	Q=Quote, O=Observation, M=Metric. Pipeline infers if omitted.
`scope_id`	No	Target scope UUID.
`file_name`	No
`mime_type`	No
`patch_ops`	No
`agent_name`	No	Signs the change.
`scope_type`	No	Scope kind; company is treated as active workspace.
`attachments`	No	1-5 files; 3 MB combined.
`document_id`	No	Living document UUID for artefact modes.
`capture_mode`	No	Knowledge routing; default signals_only.
`captured_from`	No
`change_summary`	No	Artefact change summary.
`classification`	No	Signal classification hint.
`dirty_event_id`	No	Dirty event resolved on success
`knowledge_kind`	No
`coverage_updates`	No	Snippet/idea/claim coverage updates.
`expected_content_hash`	No	content_hash from doc_patch_context
`corrects_prior_evidence`	No	signal: CORRECTS prior evidence, not repeats it.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed8 schema fields changedSep 1, 2026

addedInput schema / properties / attachments

Added value: +{
+  "description": "1-5 files; 3 MB combined.",
+  "items": {
+    "description": "PNG/JPG/WebP/PDF; no extraction.",
+    "properties": {
+      "data_base64": {
+        "description": "Base64, ≤4200000 chars.",
+        "maxLength": 4200000,
+        "minLength": 4,
+        "type": "string"
+      },
+      "file_name": {
+        "description": "Name, ≤200 chars.",
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "mime_type": {
+        "enum": [
+          "image/png",
+          "image/jpeg",
+          "image/webp",
+          "application/pdf"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "data_base64",
+      "file_name",
+      "mime_type"
+    ],
+    "type": "object"
+  },
+  "maxItems": 5,
+  "minItems": 1,
+  "type": "array"
+}

changedInput schema / properties / capture_mode / description

Previous value: -"Routing; the signals_only default creates no reusable knowledge unless requested."New value: +"Knowledge routing; default signals_only."

changedInput schema / properties / change_summary / description

Previous value: -"Public change description for update_artefact/patch_artefact (patch_artefact accepts note as fallback)."New value: +"Artefact change summary."

changedInput schema / properties / content / description

Previous value: -"Document content — update_artefact fully replaces the doc."New value: +"Knowledge or artefact content."

changedInput schema / properties / evidence / description

Previous value: -"add_artefact_evidence fields; document_id goes at top level. title aliases label, provider aliases kind."New value: +"Evidence fields; document_id is top-level."

changedInput schema / properties / items / description

Previous value: -"signal_batch; max 100 items. Each needs text + client_request_id."New value: +"signal_batch, max 100."

changedInput schema / properties / scope_id / description

Previous value: -"Required for node, claim, solution, and map scopes."New value: +"Target scope UUID."

changedInput schema / properties / text / description

Previous value: -"Raw feedback/signal text (signal mode)."New value: +"Signal text."

First observedSep 1, 2026

TDQS

C2.8/5.0

Behavior2/5

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

The annotations already indicate a destructive write operation (readOnlyHint=false, destructiveHint=true), and the description's 'update, patch or add' is consistent with that. However, the description adds no behavioral detail beyond the annotations—no mention of artefact mutation effects, idempotency keys, dirty_event_id side effects, or mode-specific consequences, which is significant for a destructive tool.

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?

The description is a single compact sentence with no filler, and the primary action is front-loaded. However, it is so terse that it fails to convey mode routing, so conciseness comes at the cost of practical guidance.

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

Completeness1/5

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

This is a high-complexity tool with 26 parameters, six modes, nested objects, and no output schema, yet the description provides only a one-sentence overview. It gives no indication of which parameters apply to which mode, no mode-specific contracts, and no behavioral caveats, leaving the agent severely under-informed for correct invocation.

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 description coverage is 81%, so the schema already documents most parameters in detail, including mode, evidence, and patch_ops. The description itself only restates broad resource categories and provides no extra parameter-level meaning, so it neither helps nor hurts beyond the high-coverage schema.

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 states a clear verb ('Capture') and resource ('Signals or knowledge') and also names additional artefact operations ('update, patch or add evidence to artefacts'). It broadly distinguishes this tool from analysis or support siblings, but it does not explain the mode-driven dispatch, so the scope remains somewhat broad.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus siblings or how to choose between the six modes in the schema. The description does not mention alternatives, prerequisites, or mode selection criteria, leaving the agent to infer usage entirely from the parameter schema.

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

All Atisbo tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool occupies a distinct functional domain: analysis, capture, connections, decisions, lookup, mapping, orientation, and support. Overlapping cases are explicitly disambiguated in descriptions, such as analyze-for-aggregates vs lookup-for-single-entities and the two non-interchangeable claim-to-node modes in map.

Naming Consistency5/5

All tools follow the same atisbo_<verb> pattern with lowercase snake_case and no mixed conventions. The prefix makes the server identity clear, and every tool name is a concise, predictable verb-like facade.

Tool Count5/5

Eight tools is a well-scoped count for a broad product surface: each tool is a compact facade grouping related modes rather than a scattered collection of one-off operations. There are no trivial or redundant tools.

Completeness5/5

The set covers the core workflow end to end: connect sources, capture signals, look up and analyze entities, map claims, make decisions, orient the workspace, and diagnose failures. Cross-references between tools fill in supporting steps like opening snippet refs and patching living docs, leaving no obvious dead ends.

Resources

Need Help?