Decision Log

Search decisions

decision_log_search_decisions

Read-onlyIdempotent

Search decisions in the authenticated workspace.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "decision_log_search_decisions"
  }
}

Input Schema

Name	Required	Description	Default
`tag`	No	Optional Tag slug filter.
`sort`	No		newest
`limit`	No
`query`	No	Search text.
`domain`	No	Optional Domain slug filter.
`offset`	No
`status`	No	Optional Decision status filter.
`projectId`	No	Optional Project identifier filter.
`currentOnly`	No
`decisionKey`	No	Optional stable Decision key filter.
`decisionType`	No	Optional Decision type filter.
`includeSuperseded`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedAug 24, 2026

TDQS

C2.1/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds the workspace scope ('in the authenticated workspace'), but nothing else about behavior—no pagination, no default limits, no return shape. Minimal value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short—a single sentence—so it is concise, but not effectively structured. It front-loads the purpose but omits any detail that would help an agent understand capabilities. Under-specification, not deliberate brevity.

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

Completeness1/5

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

For a tool with 12 optional filtering parameters, an output schema, and a rich sibling set, this description is severely incomplete. It fails to explain the search semantics, filter applicability, sorting, pagination, or how it differs from listing tools. An agent has almost nothing to go on.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description gives no insight into the 12 parameters. Schema coverage is 58% (some parameters have descriptions, some don't), but the description does not compensate for the undocumented ones (e.g., sort, limit, offset, currentOnly, includeSuperseded). It adds zero explanatory value beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: 'Search decisions'. However, it is generic and does not distinguish this tool from the many sibling list/get tools (e.g., list_decisions_by_domain, list_recent_decisions, get_current_decision). An agent cannot tell when this search is preferred over those alternatives.

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

Usage Guidelines1/5

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

There is no guidance on when to use this tool versus its siblings. No mention of which filters are appropriate for which scenarios, nor when a more specific list/get tool should be chosen. This is a significant omission given the 29 sibling tools.

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

All Decision Log tools Inspect

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

Need Help?