Skip to main content
Glama

List issues

list_issues
Read-only

Search, filter, and count Taiga project issues by type, status, open/closed, severity, priority, assignee, tag, creation/closure date, or text; results show newest first.

Instructions

List, search or count issues (bugs, questions, enhancement requests) of a Taiga project, most recently created first: reference number, type, title, status, severity, priority and assignee. Filter by type, status, open or closed, severity, priority, assignee, tag, the days they were created or closed in, or words in the text (search: "login timeout"). The heading gives the count of all matches. Planned work is user stories: use list_user_stories. For the description and comments of one issue use get_item.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project": "<project>"
    },
    "name": "list_issues"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoOnly items that carry this tag, e.g. "backend". get_project lists the tags of a project.
pageNoWhich part of a long list, counted from 1. When an answer says more items exist, call again with the next page and the same `limit` and filters.
typeNoExact issue type name, e.g. "Bug". A wrong name is answered with the valid ones.
limitNoMost items to return in one answer (default 30, at most 100). The answer says how many more exist.
closedNofalse: only items still open ("not done yet", "remaining"). true: only closed ones. Leave out for both.
searchNoWords to look for in titles, descriptions and tags, e.g. "invoice export". An item must contain every word; a word also matches the beginning of a longer one. Use it when the user describes an item instead of giving its number.
statusNoExact status name, e.g. "Needs Info". Each project defines its own; a wrong name is answered with the valid ones. For "open" or "done" in general use `closed` instead.
projectYesProject slug as given by list_projects, e.g. "acme-billing". Not the display name.
priorityNoExact priority name, e.g. "High". A wrong name is answered with the valid ones.
severityNoExact severity name, e.g. "Critical". A wrong name is answered with the valid ones.
created_toNoOnly items created on or before this day, as YYYY-MM-DD (UTC).
assigned_toNoOnly items assigned to this person: full name or username as in Taiga; part of the name is enough when it fits one member only, and accents may be left out. "unassigned" for items assigned to nobody. A name that does not fit is answered with the members. For the signed-in user use `assigned_to_me`.
finished_toNoOnly items closed on or before this day, as YYYY-MM-DD (UTC). Items still open are left out.
created_fromNoOnly items created on or after this day, as YYYY-MM-DD (UTC).
finished_fromNoOnly items closed on or after this day, as YYYY-MM-DD (UTC). Items still open are left out.
assigned_to_meNotrue: only items assigned to the signed-in user ("my stories", "assigned to me").

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the rest and does so: ordering ('most recently created first'), the count in the heading, pagination behavior ('the answer says how many more exist'), and self-correcting errors ('a wrong name is answered with the valid ones'). It further discloses search semantics (all words must match, prefix matching) and fuzzy assignee matching including 'unassigned'.

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?

Three sentences, each front-loaded with the highest-value information: capability and ordering first, filters second, sibling routing third. No filler or repetition of the title.

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 16-parameter list tool with no output schema, the description covers what is returned (field list plus count heading), how paging continues, and how invalid filter values are handled. Nothing an agent needs to call it correctly is missing.

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%, so the schema already defines all 16 parameters in detail. The description's filter enumeration mirrors the schema and adds only a search example ('login timeout'), which is marginal. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb set (list, search, count) plus the resource (issues of a Taiga project), names the returned fields (reference number, type, title, status, severity, priority, assignee) and the sort order. It also explicitly excludes siblings: planned work is list_user_stories, single-item detail is get_item.

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

Usage Guidelines5/5

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

Gives explicit routing rules: 'Planned work is user stories: use list_user_stories' and 'For the description and comments of one issue use get_item'. It also states when the search filter applies ('when the user describes an item instead of giving its number'), which is real when-to-use guidance rather than a restatement of the schema.

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