Skip to main content
Glama

docs-search

Search Exeris documentation for a literal, case-insensitive substring and return each match's path, line number, and snippet; optionally narrow results to files whose relative path contains a filter.

Instructions

Search exeris-docs for a literal substring (case-insensitive). Returns the path, line number, and snippet of each match, capped by maxResults. Optional pathFilter narrows to files whose docs-root-relative path contains the substring (e.g. 'adr/' to scope to ADR files). Scope is the docs root only; cross-repo content is reachable via get_adr.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "docs-search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesLiteral substring to search for (case-insensitive). Required, must be non-empty after trim.
maxResultsNoMaximum hits to return (default 50, hard cap 200).
pathFilterNoOptional substring; only files whose relative path contains this string are scanned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does reasonably well: it discloses the result shape (path, line number, snippet), the truncation behavior via maxResults, and the scope limitation that only docs-root content is scanned. It leaves out whether matching is line-based or full-text across newlines, and says nothing about result ordering or a read-only/no-side-effect confirmation.

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?

Three sentences, front-loaded with what it does, then return shape and cap, then the scope constraint and escape hatch. Every sentence contributes new information and nothing is duplicated verbatim from the schema.

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

Completeness4/5

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

For a three-parameter read-only search with no output schema, the definition covers purpose, matching semantics, result contents, caps, and scope boundary — enough to invoke it correctly. Minor gaps remain around no-match behavior and ordering, which matter slightly for a search tool whose output an agent must interpret.

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 value beyond the schema by giving a concrete pathFilter example ("'adr/' to scope to ADR files") and by tying maxResults to the result cap. The two remaining params are otherwise just restated, so it is not a full 5.

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 and resource ("Search exeris-docs for a literal substring") and immediately pins down the matching semantics (case-insensitive, literal). It also distinguishes itself from the sibling get_adr by declaring its scope boundary: "Scope is the docs root only; cross-repo content is reachable via get_adr."

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?

It clearly states the domain of applicability (docs root only) and names get_adr as the route for anything outside that scope, which is real routing guidance. It does not explicitly contrast with the other per-document siblings (get_repo_doc, get_template, get_whitepaper), so an agent must infer that those fetch rather than search.

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