Skip to main content
Glama

subscribe_observation

Read-onlyIdempotent

Subscribe to live presence updates at your current POI and system (Change-feed alternative to polling get_nearby and get_system_agents. Anchors a watch at your current POI and system: the response is a full baseline snapshot (uncloaked players nearby and system-wide, the pirates/empire_npcs/creatures, intact prizes and arena_npcs at your POI that get_nearby returns, plus the unknown_signature hint), and thereafter you receive observation_update messages only when that presence changes — players arriving, leaving, going online/offline, or changing ship/faction/combat state; pirates/empire NPCs/creatures arriving, leaving, or changing (hull, status, combat) via pirates_changed/pirates_departed, empire_npcs_changed/empire_npcs_departed, creatures_changed/creatures_departed; intact prizes arriving, leaving, or changing via prizes_changed/prizes_departed; and arena challenge enemies joining or changing (hull, shield, status, flees) via arena_npcs_changed, with arena_npcs_departed carrying enemies removed when their match ends. A knockout is a change, not a departure: a knocked-out enemy keeps appearing at hull 0 until its match ends, so do not read a missing arena_npcs_departed entry as the enemy still fighting. arena_npcs is absent unless an NPC challenge match is running at your POI; while one is, expect an arena_npcs_changed entry most ticks because enemy hull and shield move constantly. Pirate baseline and pirates_changed entries include faction (the stronghold crew and pirate-standing counterparty), faction_name, and primary_color/secondary_color livery as #RRGGBB when configured. Avoids re-fetching the full list every tick. The watch ends automatically when you travel, jump, or disconnect; re-subscribe after moving. Cloaked players are hidden, same visibility rules as get_nearby. Set active_scan:true to also run a continuous sensor sweep that resolves cloaked ships (the same contest as the scan command, with tiered reveal) and reports them via cloaked_resolved/cloaked_lost — this requires a scanner and being undocked, burns 1 fuel/tick, alerts cloakers when it locks them, and turns off automatically when you run out of fuel. It replaces looping the scan command to hunt cloaked traffic. Over MCP/HTTP, observation_update arrives via get_notifications under the 'observation' type (it was previously lumped into 'system').)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_idYesYour session ID from login/register
active_scanNoAlso run a continuous active sensor sweep that resolves cloaked ships (requires a scanner, must be undocked, burns 1 fuel/tick, alerts cloakers). Omit or false for the passive presence feed only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Far exceeds the readOnlyHint/idempotentHint annotations: it details the full baseline snapshot contents, each update message type, knockout-vs-departure semantics, arena_npcs absence conditions, cloaked-player visibility, watch lifecycle, active_scan side effects (scanner required, must be undocked, 1 fuel/tick, alerts cloakers, auto-off on empty fuel), and the MCP notification channel. This is rich behavioral disclosure beyond structured fields.

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?

Front-loaded with the core purpose and densely informative, but delivered as one massive single-paragraph run-on. Given the number of message types and edge cases there is little waste, yet the wall-of-text format hurts scannability and would benefit from structure.

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?

No output schema exists, and the description fully compensates by explaining the baseline snapshot, the update-message taxonomy, edge cases, and delivery channel. For a complex subscription tool, 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.

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds genuine meaning to active_scan beyond the schema: it ties it to 'the same contest as the scan command, with tiered reveal,' names the report messages (cloaked_resolved/cloaked_lost), and notes auto-disable on fuel exhaustion.

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 and resource ('Subscribe to live presence updates at your current POI and system') and immediately distinguishes itself from siblings by framing itself as a 'Change-feed alternative to polling get_nearby and get_system_agents.' An agent can tell exactly what this tool does and how it differs from the polling alternatives.

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?

Explicitly says when to use it (change-feed instead of polling get_nearby/get_system_agents), when the subscription ends ('when you travel, jump, or disconnect; re-subscribe after moving'), and names the alternative for the cloaked-hunt case (active_scan 'replaces looping the scan command'). Usage conditions and alternatives are fully spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources