Skip to main content
Glama

SUNAGO Matrix

by com.sunago-matrix

Get projects

projects_get
Read-onlyIdempotent

List projects the signed-in user can see for project management (RLS-scoped). Do not use this to choose where to log time; use timelog_get_loggable_projects for time registration. IMPORTANT - status 'Completed' does NOT always mean finished. A nightly automation moves any project past its end_date to Completed and archives it, and the manager still has to decide whether to confirm it or reactivate it with a new end date. Those projects carry awaiting_manager_decision: true, and reporting one as 'completed' is wrong: the work is unresolved, not done. Filter with awaiting_decision: true (optionally with a manager) to answer 'what is waiting for me'. DEFAULTS TO ACTIVE PROJECTS ONLY - not archived, and not Completed, Cancelled or Archived. Say so when you answer ("you have 20 active projects"), and read meta.scope_note. Pass scope: archived or all when the question spans finished work - project economics over time, what was delivered last year. One exception, handled for you: projects awaiting a manager decision ARE archived, so awaiting_decision: true widens the scope to include them rather than returning an empty list. Max limit 200 - the response always carries pagination.total (full match count) plus has_more/next_cursor. NEVER count or total projects from one page while has_more is true.

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.
searchNoMatch project title.
statusNo
archivedNoExplicit override. Setting it wins over scope.
manager_idNoemployees.id of the project manager. Combine with awaiting_decision to get one manager's outstanding decisions.
awaiting_decisionNotrue returns only projects the automation closed and nobody has decided on yet. These are archived, so do not combine with archived: false.

Output Schema

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

TDQS

A5/5.0
Behavior5/5

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses critical behavioral nuances: the 'Completed' status does not mean finished due to a nightly automation, awaiting_manager_decision projects are archived and must not be reported as completed, and the default scope is active only unless explicitly widened. It also reveals pagination behavior (max 200, total/has_more/next_cursor) and warns against counting while has_more is true.

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?

Although long, every sentence earns its place by conveying a distinct operational fact or guardrail. The description is front-loaded with the core purpose and sibling exclusion, then moves into scoping nuances and pagination warnings. No filler or repetition is present.

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 9-parameter, 0-required list tool with an output schema, the description covers default behavior, edge cases, automation side effects, reportable statuses, pagination, and explicit agent instructions. The presence of an output schema means return fields need not be enumerated, and nothing essential is missing for an agent to invoke this tool correctly.

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

Parameters5/5

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

With 89% schema coverage, the baseline is 3, but the description adds substantial meaning beyond the schema: it clarifies that awaiting_decision widens scope because those projects are archived, explains the semantics of status 'Completed', and provides concrete advice for scope choices. It also explains pagination-related limit behavior and the manager_id combination with awaiting_decision.

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 the exact operation: 'List projects the signed-in user can see for project management (RLS-scoped).' It clearly identifies the resource (projects) and scope (signed-in user), and distinguishes itself from sibling tools like timelog_get_loggable_projects by explicitly saying 'Do not use this to choose where to log time.'

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?

The description gives explicit when-to-use and when-not-to-use guidance, naming the alternative timelog_get_loggable_projects for time registration. It also instructs on when to use scope archived/all (finished work, historical questions) and how to use awaiting_decision for 'what is waiting for me' inquiries.

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