Skip to main content
Glama
Sign In
phabricator-mcp

phabricator-mcp

by freelancer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

phabricator_task_search

Read-only

Search Maniphest tasks by status, project, assignee, author, priority, dates, full-text query, and other filters with pagination to find relevant work items.

Instructions

Search Maniphest tasks with optional filters

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": "phabricator_task_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNoCursor for next-page pagination
limitNoMaximum results (max 100)
orderNoResult order: "priority", "updated", "outdated", "newest", "oldest", "closed", "title", "relevance"
beforeNoCursor for previous-page pagination
queryKeyNoBuilt-in query: "all", "open", "authored", "assigned", "subscribed"
attachmentsNoData attachments to include
constraintsNoSearch constraints
includeEmptyCustomFieldsNoAlso return custom fields that have no value, as null, to see every custom field key a task can take

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.0
    • addedInput schema / properties / includeEmptyCustomFields
      Added value: +{
+  "description": "Also return custom fields that have no value, as null, to see every custom field key a task can take",
+  "type": "boolean"
+}
  2. First observedv2.0.19

TDQS

C2.7/5.0
Behavior3/5

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

readOnlyHint=true already tells the agent this is a safe read with no side effects, so the bar for the description is lower. The description adds nothing beyond that: no mention of pagination behavior (the after/before/limit cursors), default result ordering, or the fact that constraints combine as AND filters. No contradiction with 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?

A single seven-word sentence is certainly front-loaded and waste-free, but it is undersized rather than concise. For a tool with a deeply nested 26-field constraints object, one sentence leaves too much unsaid for the brevity to count as a virtue.

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

Completeness2/5

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

This is a complex search tool with nested objects, cursor pagination, built-in query keys, and attachment toggles, and the description addresses none of it. The rich schema compensates for parameter documentation, but an agent still lacks guidance on filter combination semantics, paging workflow, or how this differs from the narrower task search siblings.

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 nested constraints object documents all 26 filter fields with types and meanings, so the schema does the heavy lifting. The description contributes nothing to parameter meaning — it doesn't even name the constraints/queryKey/attachments parameters — which is acceptable at this coverage level but not additive.

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?

"Search Maniphest tasks" names a verb and a resource, but the qualifier "with optional filters" is filler that adds no discriminating information. Siblings like phabricator_task_status_search and phabricator_task_priority_search overlap heavily with this tool, and the description gives no basis for telling them apart.

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

Usage Guidelines2/5

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

No statement of when to reach for this tool rather than the specialized task_status_search or task_priority_search siblings, nor any note that this is the general-purpose query entry point. The word "optional" is the only hint that all filters may be omitted.

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