Skip to main content
Glama

find_evidence

Read-only

Search vault docs for a concept title and get ranked matches with prose excerpts, showing where the concept appears 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 Do not cite a non-node as graph evidence without saying so. Pass limit for the top-N. 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
NameRequiredDescriptionDefault
limitNoReturn only the top-N highest-scoring matches. Omit for all matches (still ranked).
titleYesConcept title to search for (case-insensitive substring match).
nodesOnlyNoReturn 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
NameRequiredDescriptionDefault
queryYes
matchesYes
bodyHintNoOnly present when at least one match returned a partial excerpt — names the get_concepts({ body: "full" }) call that returns the rest.
growthHintNoOnly present when matches is empty — near-titled vault node(s) to check, or an add_concept scaffold, derived from the real vault title set.
nonNodeHintNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotation's readOnlyHint: true, the description discloses substantial behavioral details: it produces ranked matches with a deterministic score formula (title match > frontmatter > body, plus tie-breakers), includes prose excerpts up to 200 chars avoiding certain blocks, distinguishes nodes vs non-nodes, and clarifies the growthHint on zero matches. This is genuinely useful behavioral context not present in any other structured field.

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 organized so the core purpose and use case lead, followed by the ranking rules, node semantics, and the limit/growthHint behaviors. The length is justified because of the tool's complexity, but it is dense and could lose agents scanning quickly. Still, every sentence earns its place.

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?

The description, combined with the fully enumerated input schema and an existing output schema, leaves few important gaps. It covers purpose, use context, matching and ranking behavior, node/non-node semantics, the limit option, and the zero-result growthHint, so it is effectively complete for correct invocation and result interpretation.

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 100%, so the baseline is 3. The description references limit, nodesOnly, and the title's substring semantics, but these largely duplicate what the schema already says (e.g., 'Return only the top-N highest-scoring matches' and the nodesOnly default flag). It adds no fundamentally new parameter-level meaning.

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 'Find vault docs that mention a given concept by title,' a specific verb+resource+scoping statement. It clearly positions the tool for the 'where is this capability realized' use case, and the emphasis on title-based mention matching differentiates it from sibling tools like find_backlinks, find_neighbors, and get_concept.

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?

The description is explicit about when to use it: 'Useful when an AI agent asks where a capability is reified in code or docs.' It also explains it can avoid an extra get_concept call. However, it does not explicitly state exclusions (e.g., 'for backlink relationships use find_backlinks'), leaning on implied differentiation rather than naming alternative siblings.

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