Search the drillable publication. scope is optional — omitted searches everything (the root scope); a party or work address (e.g. /make-noise or /make-noise/modules@v1) narrows. Returns addresses + where-matched + grade, or an honest abstain (logged as demand).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| scope | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / domainRemoved value: -{
- "description": "Optional: restrict to one domain.",
- "type": "string"
-}Input schema / properties / query / descriptionRemoved value: -"What to search for."Input schema / properties / scopeAdded value: +{
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden and does well: it discloses the return shape (addresses + where-matched + grade), the honest abstain behavior, and the demand-logging side effect. It doesn't cover auth or rate limits, but for a search operation these are less critical.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three dense sentences with no wasted words. The main action is front-loaded, and every clause adds semantic value — scope semantics, return format, and abstain behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple 2-parameter schema, no annotations, and no output schema, the description covers the essential elements: what it searches, scope options, and return contract. Minor jargon like 'drillable', 'grade', and 'demand' is left unexplained, but an agent can still invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It thoroughly explains the scope parameter (omitted = root scope; party/work address narrows) with examples, but the query parameter is not described and is left to inference by its name. Partial compensation yields a mid score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Search the drillable publication.' It also details the scope behavior and return values, which makes the tool's function clear. However, it does not explicitly differentiate from the sibling tool 'drill', so it lacks full sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context on when to use the tool: search broadly when scope is omitted, or narrow to a party/work address when provided, with concrete examples. It does not mention when to prefer the sibling tool or state exclusions, so it stops short of full alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Drill and search have clearly distinct roles: drill retrieves a specific address/resource, while search discovers addresses by querying the publication. There is no meaningful overlap between the two operations.
Both tool names are single, lowercase imperative verbs that follow a consistent and predictable pattern. The naming matches the server's drillable-publication concept well.
Two tools is slightly below the typical range, but each tool is broad and earns its place in a focused read-only publication server. The surface feels a little thin, but not unreasonably so.
Within the apparent read-only domain, drill and search cover the essential operations: retrieving a known address and discovering addresses via search. No obvious dead ends or missing core capabilities are evident.