Skip to main content
Glama

Linear

by io.github.pipeworx-io

Linear List Issues

linear_list_issues
Read-onlyIdempotent

Browse issues in your Linear workspace, filtered by TEAM, DATE RANGE, state, priority, assignee, project, cycle, or labels — alone or combined. filter is Linear's own IssueFilter, so anything IssueFilter expresses works here: filter one team ({"team":{"key":{"eq":"ENG"}}}), a date window ({"updatedAt":{"gte":"-P2W"}}), or several DIFFERENT filter sets at once via or. Returns issue ID, title, state, priority, assignee, and URL, newest-updated first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
firstNoNumber of issues to return (default 20, max 50)
filterNoOptional Linear IssueFilter, passed straight through to the issues query. Send it as an object, or as a JSON string — both work. TEAM: {"team":{"key":{"eq":"ENG"}}} (also team.id / team.name). DATE: {"updatedAt":{"gte":"2026-08-01"}} — also createdAt, completedAt, startedAt, canceledAt, with eq/gt/gte/lt/lte/in/nin. Dates take an ISO 8601 datetime, a shortcut like "2026", or an ISO DURATION relative to now: {"updatedAt":{"gte":"-P2W"}} is "in the last two weeks". STATE: {"state":{"name":{"eq":"In Progress"}}} (or state.type for "started"/"completed"/"canceled"). COMBINE by putting keys side by side — {"team":{"key":{"eq":"ENG"}},"updatedAt":{"gte":"-P1W"}} is ENG issues touched this week (AND). For several DIFFERENT sets in one call, use `or`: {"or":[{"team":{"key":{"eq":"ENG"}},"state":{"name":{"eq":"In Progress"}}},{"team":{"key":{"eq":"DES"}},"state":{"name":{"eq":"Backlog"}}}]}. `and` nests the same way.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
issuesYesList of issues matching the filter

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare the safety profile (read-only, idempotent, non-destructive). The description adds the return fields (ID, title, state, priority, assignee, URL), the ordering (newest-updated first), and that filter is passed through as Linear's IssueFilter. This adds genuinely useful behavior context 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.

Conciseness5/5

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

Two sentences, both information-dense: the first front-loads the operation and filter dimensions, the second gives the filter semantics and return shape. No filler or repetition of schema content.

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

Completeness5/5

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

For a 2-parameter tool with no required parameters, a detailed input schema, rich annotations, and an output schema, the description covers what an agent needs to call it correctly: filter capabilities, pass-through behavior, return fields, and ordering. Nothing essential is missing.

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%, with very detailed filter syntax documentation. The description adds the useful generalization that 'anything IssueFilter expresses works here' and highlights combining filters and the `or` form, which goes beyond the schema's examples and reinforces the parameter's flexibility.

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 states a specific verb and resource ('Browse issues in your Linear workspace') and the full scope of filtering (team, date range, state, priority, assignee, project, cycle, labels). This clearly differentiates it from sibling tools like linear_get_issue, linear_create_issue, and linear_list_teams.

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 description makes clear this is the tool for browsing/filtering issues by structured fields, alone or combined. It does not explicitly name linear_search as the alternative for keyword-style search or linear_get_issue for single-issue lookup, but the context is clear enough for an agent to select it for structured issue listing.

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

All Linear toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, especially within their domains (e.g., Polymarket tools are well-separated). However, a few tools like ask_pipeworx, deep_research, and suggest_questions could cause minor confusion, as they all deal with querying data.

Naming Consistency3/5

Tools from the same service use consistent prefixes (linear_, polymarket_, pipeworx_), but the overall naming style is mixed: some are verb_noun (linear_create_issue), some are noun_verb (bet_research), and some are single words (remember). This inconsistency reduces predictability.

Tool Count3/5

With 35 tools, the server covers a broad range of functionality (data query, prediction markets, memory, etc.). While not excessive, the count is on the higher side, and the server name 'Linear' suggests a narrower focus, which may mislead expectations.

Completeness4/5

The tool set covers core data querying, research, entity profiles, prediction market analysis, and memory operations comprehensively. Minor gaps exist (e.g., limited Linear CRUD), but the overall surface feels complete for its intended use as a data assistant.

Resources