Skip to main content
Glama

explain

Read-only

Shows the evidence behind one recorded mark: the files and patterns searched, how counts were reached, and what was left out, so an agent can verify the finding before acting on it.

Instructions

Returns the evidence behind one mark, computed again: the files and patterns searched, the counts and what was left out.

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": {
      "repository": "<repository>",
      "mark": "<mark>"
    },
    "name": "explain"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoThe revision to compare with: a commit, a tag or a branch. When it is not an ancestor of the head, their merge base is used and the answer says so. Without it, the default base the repository declares in .plimsoll.toml is used.
markYesThe identifier of one mark, as status or report printed it, for example shape.file-size:src/store.ts.
repositoryYesAbsolute path of the repository: its top folder or any folder inside its working tree.

Output Schema

NameRequiredDescriptionDefault
baseYes
headYes
moreYes
marksYes
countsYes
historyYes
touchedYes
versionYes
evidenceNo
questionYes
resolvedYes
sectionsNo
standingYes
detectorsYes
footprintNo
summariesYes
reportOnlyYes
notAnalysedYes
acknowledgedNo
acknowledgedInNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description's job is to add the parts annotations cannot express. It does: the evidence is recomputed rather than replayed, and the answer deliberately includes exclusions ("what was left out") alongside searched files, patterns and counts — a non-obvious disclosure that the result is self-auditing. It stops short of saying whether recomputation is expensive or could differ from what status reported.

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?

A single front-loaded sentence with a colon-delimited enumeration; no filler and no repeated framing. The enumeration edges toward restating what the output schema already carries, which keeps it just below maximum.

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?

The tool is a read-only explainer with annotations supplying safety semantics, a full output schema, and completely documented parameters, so the description only needs to convey intent and freshness of computation — which it does. The remaining gap is workflow placement relative to status and report, which the definition leaves to inference.

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% and the schema itself is unusually strong, spelling out merge-base fallback behavior for base and giving a concrete example value for mark. The description adds nothing beyond that, so baseline 3 applies.

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?

A specific verb ("Returns") with a specific resource ("the evidence behind one mark"), plus a scoping qualifier "computed again" that signals this re-derives the proof rather than echoing a cached result. It is clearly a different operation from report/status, which merely print mark identifiers, though the description never names those siblings to make the contrast explicit.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: an agent can infer this is the drill-down to call after status/report surfaced a mark, an inference reinforced only by the schema note "as status or report printed it." There is no explicit when-to-use, no when-not-to-use, and no stated alternative for retrieving evidence.

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

Deploy Server

Other Tools