ontology-atlas

Overview Schema Source Related Servers Discussions Admin

find_evidence

Read-only

Find vault docs mentioning a concept by title, ranked by relevance with excerpts. Helps AI agents locate where a capability is realized in code or docs.

Instructions

Find vault docs that mention a given concept by title. Useful when an AI agent asks where a capability is realized in code or docs. Each match includes a prose excerpt (max 200 chars, headings/tables/code skipped) so agents see what the matching doc says without an extra get_concept call. Matches are RANKED by a deterministic relevance score (title match > frontmatter ref > body, plus a title token-overlap tiebreaker), then by whether the doc is a graph node, then slug — best-first. A vault holds ordinary markdown too (meeting notes, memos, drafts have no kind: and are not graph nodes); every row says which it is via isNode, non-nodes rank below nodes of equal relevance, and nodesOnly: true filters them out. Do not cite a non-node as graph evidence without saying so. Returns the best 50 by default (limit up to 500), with total matches and limited when more matched. When zero docs mention the title, the response includes a growthHint — near-titled vault nodes to check first, or an add_concept scaffold if the concept looks genuinely new.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Return only the top-N highest-scoring matches. Defaults 50; `total` and `limited` say whether more matched.
`title`	Yes	Concept title to search for (case-insensitive substring match).
`nodesOnly`	No	Return only graph nodes (docs with a `kind:`). Default false — ordinary markdown in the same folder is included and marked `isNode: false`.

Output Schema

TableJSON Schema

Name	Required	Description
`query`	Yes
`total`	No	Every document that matched, before `limit`.
`limited`	No	True when `matches` holds fewer rows than `total`.
`matches`	Yes
`bodyHint`	No	Only present when at least one match returned a partial excerpt — names the get_concepts({ body: "full" }) call that returns the rest.
`limitHint`	No	Only present when `limited`: how to narrow the search or raise `limit`.
`growthHint`	No	Only present when matches is empty — near-titled vault node(s) to check, or an add_concept scaffold, derived from the real vault title set.
`nonNodeHint`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.4.0Oct 1, 2026

changedInput schema / properties / limit / description

Previous value: -"Return only the top-N highest-scoring matches. Omit for all matches (still ranked)."New value: +"Return only the top-N highest-scoring matches. Defaults 50; `total` and `limited` say whether more matched."

addedOutput schema / properties / limitHint

Added value: +{
+  "description": "Only present when `limited`: how to narrow the search or raise `limit`.",
+  "type": "string"
+}

addedOutput schema / properties / limited

Added value: +{
+  "description": "True when `matches` holds fewer rows than `total`.",
+  "type": "boolean"
+}

addedOutput schema / properties / total

Added value: +{
+  "description": "Every document that matched, before `limit`.",
+  "minimum": 0,
+  "type": "integer"
+}

First observedv0.13.0Sep 11, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations cover the safety profile (readOnly, non-destructive), so the bar is lower, yet the description still discloses substantial behavior: excerpt truncation at 200 chars with heading/table/code skipping, the deterministic ranking order (title > frontmatter > body, node-ness, slug), default 50 / max 500 with total and limited flags, and the growthHint on zero matches. This is far more than the annotations carry.

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?

Front-loads the core purpose and is generally efficient, with the most actionable routing and ranking facts early. It is dense and long with heavy bold/caps formatting, and a few clauses (e.g. the full ranking tiebreaker chain) could be tightened, but every sentence carries information.

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?

For a 3-param search tool with an output schema, the description supplies everything needed to call it correctly and interpret results: node vs non-node semantics, ranking, limit/truncation signals, and the empty-result growthHint path. No behavioral or usage gap an agent would need remains.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it explains that limit defaults to 50 and that total/limited signal truncation, and that nodesOnly filters ordinary markdown that would otherwise rank below nodes. It clarifies the intent of each parameter rather than restating types.

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?

States a specific verb and resource ('Find vault docs that mention a given concept by title') and distinguishes itself from siblings like get_concept by providing the excerpt inline. An agent can tell instantly that this is a ranked text search over vault docs rather than a concept fetch.

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?

Gives a concrete trigger ('when an AI agent asks where a capability is realized in code or docs') and a caution ('Do not cite a non-node as graph evidence without saying so'), which is a real usage constraint. It does not explicitly route against alternatives like get_concept or query_concepts beyond the passing mention, so it stops short of full when/when-not guidance.

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