Skip to main content
Glama

SUNAGO Matrix

by com.sunago-matrix

Get tasks

tasks_get
Read-onlyIdempotent

List tasks (RLS-scoped). Every row carries blocked and blocked_by: a task can be perfectly ready in every other respect and still be unstartable because something it waits on is not Done. NEVER tell anyone to get on with a task without saying it is blocked, and prefer an unblocked one when asked what to pick up. DEFAULTS TO ACTIVE TASKS ONLY - archived ones are excluded. Done tasks in a live project ARE included, the same as the board in Matrix shows them. Say so when you answer ("you have 7 active tasks"), and read meta.scope_note. Pass scope: archived or all only when the question is about finished or historical work. Optional filters: project, assignee, status. Max limit 200 - the response always carries pagination.total (full match count) plus has_more/next_cursor. Do not count or total these rows while has_more is true. NOTE: time is logged on projects, not tasks, so there is no per-task actual-hours figure. est_hours is the estimate; do not infer spent or remaining hours from these rows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax 200.
scopeNoactive (default) covers only what is still live. Use archived for finished or lost records, or all when the question spans both - historical revenue, deals closed over a period, anything measured across time. Always tell the user which set your answer covers.active
cursorNoOpaque cursor from a previous response's pagination.next_cursor. Preferred over offset: keyset paging never skips or duplicates rows.
offsetNoRow offset for offset-based paging. Ignored when cursor is supplied.
statusNo
blockedNotrue returns only tasks waiting on unfinished work; false only those that can be started.
archivedNoExplicit override. Setting it wins over scope.
project_idNo
assignee_idNoFilter to tasks this person is assigned to.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
metaNo
tasksYes
warningNoPresent only when the page is truncated.
paginationYes

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already mark this as read-only and idempotent, but the description adds substantial behavioral detail beyond them: RLS scoping, default-to-active behavior, inclusion of done tasks, max limit 200, pagination.total/has_more/next_cursor, the blocked/blocked_by semantics, and the warning not to infer hours from est_hours. None of this contradicts the annotations.

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

Conciseness4/5

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

The description is dense and long, but nearly every sentence carries a warning or decision rule that matters for correct use, such as the blocked task warning, the has_more counting rule, and the hours caveat. It front-loads the core purpose and then layers critical behavioral constraints; a bulleted structure would improve readability, but the content earns its place.

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?

Given the tool's complexity, the output schema, and the annotations, the description covers everything an agent needs: default scope, archived/all behavior, optional filters, max limit, pagination completeness indicators, blocked-task handling, and the est_hours limitation. Context is complete for safe and correct invocation.

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 78%, so the schema already documents most parameters such as scope, cursor, offset, blocked, archived, and assignee_id. The description adds useful usage context around scope and the optional filters project, assignee, status, but it does little to explain status values or project_id beyond the schema. This is adequate but not exceptional compensation.

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

Purpose4/5

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

The description opens with a specific verb and resource: "List tasks (RLS-scoped)." It clearly identifies the tool as the general task-listing operation and adds meaningful context about active/archived scoping and filters. However, it does not explicitly distinguish itself from sibling tools like tasks_get_dependencies, relying on the resource name rather than naming alternatives.

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 gives strong when-to-use guidance: use the default active scope unless the question is about finished or historical work, pass scope: archived or all only in those cases, and tell the user which set the answer covers. It also warns against using the rows for hours because "time is logged on projects, not tasks." It does not explicitly name alternative tools for dependency or time queries, so it falls just 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.

All SUNAGO Matrix 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

B3.4/5.0
Disambiguation4/5

Most tools follow a clear resource+action pattern and the descriptions are unusually precise about boundaries. A few near-overlaps remain: projects_get_finance vs projects_get_financials, and notes_create vs crm_log_activity on a deal are both plausible for recording a note on a deal.

Naming Consistency4/5

The domain_prefix_action convention is consistent across nearly all tools, e.g. crm_create_lead, projects_update_risk, timelog_approve_time. Deviations include standalone list_trash, meta tools like whoami/tool_search/tool_invoke, and the confusing projects_get_finance/projects_get_financials pair.

Tool Count1/5

With 105 tools, this far exceeds the 50+ threshold defined as an extreme mismatch. Even for a full ERP/CRM suite, the fine-grained split—39 project tools alone—creates a massive tool-selection surface that is hard for an agent to navigate reliably.

Completeness4/5

The surface covers CRM, projects, tasks, time/expenses, HR, notes, notifications, contracts, and reporting with create/read/update/delete for most primary entities. Minor gaps exist: crm_log_activity has no read-back path, contracts lack delete/restore, and proposals are intentionally read-only, but agents can work around these.

Resources