Skip to main content
Glama

Ferritin — Rust documentation

by rs.ferritin
OverviewDiscussionsAdmin

search

Read-onlyIdempotent

Search for items within a crate's documentation, or — without a crate — discover which crate to use.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
crateNoCrate to search within, optionally with an `@`-suffixed semver requirement (not an exact version): `serde`, `tokio@1` (newest 1.x), or `tokio@=1.40` to pin an exact release. **Omit only to discover which crate to use.** With `crate`, the search runs over that crate's full documentation — item names and prose. Without it, it searches a different, much shallower dataset: crates.io crate names, descriptions, and declared keywords. It returns crates, not items, and cannot see any crate's actual documentation. If you already know the crate name, always pass it.
queryYesSearch query — one or more complete words. With `crate`, matched against item names and documentation prose; without it, against crate names, descriptions, and declared keywords.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "crate": "serde",
-    "description": "Find deserialization items in serde",
-    "query": "deserialize"
-  }
-]New value: +[
+  {
+    "crate": "serde",
+    "description": "Find deserialization items in serde",
+    "query": "deserialize"
+  },
+  {
+    "description": "Discover which crate to use for MQTT",
+    "query": "mqtt client"
+  }
+]
    • changedInput schema / properties / crate / description
      Previous value: -"Crate to search, optionally with an `@`-suffixed semver requirement (not\nan exact version): `serde`, `tokio@1` (newest 1.x), or `tokio@=1.40` to\npin an exact release."New value: +"Crate to search within, optionally with an `@`-suffixed semver\nrequirement (not an exact version): `serde`, `tokio@1` (newest 1.x), or\n`tokio@=1.40` to pin an exact release.\n\n**Omit only to discover which crate to use.** With `crate`, the search\nruns over that crate's full documentation — item names and prose.\nWithout it, it searches a different, much shallower dataset: crates.io\ncrate names, descriptions, and declared keywords. It returns crates,\nnot items, and cannot see any crate's actual documentation. If you\nalready know the crate name, always pass it."
    • changedInput schema / properties / query / description
      Previous value: -"Search query — one or more words matched against item names and prose."New value: +"Search query — one or more complete words. With `crate`, matched\nagainst item names and documentation prose; without it, against crate\nnames, descriptions, and declared keywords."
    • changedInput schema / required
      Previous value: -[
-  "crate",
-  "query"
-]New value: +[
+  "query"
+]
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations establish the tool as read-only, idempotent, and non-destructive. The parameter description adds valuable behavioral nuance beyond these annotations, explaining that without a crate the search runs over a 'much shallower dataset' and 'cannot see any crate's actual documentation.'

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?

The one-sentence description is extremely compact and front-loaded with the verb 'Search.' It efficiently communicates both usage modes with no wasted words or repetition of schema information.

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 definition is largely complete: annotations cover safety, the schema thoroughly explains parameter behavior, and the description clarifies the dual-mode nature. However, there is no output schema and the description does not state return format or pagination, which is a minor gap for a search tool.

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% and the parameter descriptions are exceptionally detailed, including version syntax, examples, and mode-dependent behavior. The main description also contributes semantic meaning by indicating that `crate` is optional and changes the search target.

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 clearly states the verb 'Search' and distinguishes two resources: items within a crate's documentation, or crates themselves when no crate is given. It effectively differentiates this search tool from the sibling 'get' tool by emphasizing discovery across documentation.

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 input schema provides explicit usage guidance: 'Omit only to discover which crate to use' and 'If you already know the crate name, always pass it.' This gives clear decision criteria for when to use each mode, though alternatives like the sibling 'get' tool are not mentioned.

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

All Ferritin — Rust documentation toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources