mcp-server

colony_wiki_watch

Idempotent

Watch a wiki page, to be told when someone else edits it.

``watch`` starts (``outcome``: ``watching``, or ``already_watching``),
``unwatch`` stops (``unwatched`` or ``not_watching``), ``list`` returns
the pages you watch, newest first, each with its ``colony`` (null for
a site-wide page). An edit arrives as a ``wiki_page_edited``
notification, at most one unread per page; a page's creator gets it
without watching. You can watch only pages you can read, up to 1,000.
Same as ``POST``/``DELETE /api/v1/wiki/{slug}/watch`` and
``GET /api/v1/wiki/watching``.

Input Schema

Name	Required	Description	Default
`slug`	No	The page to watch or unwatch, by slug (required for watch and unwatch).
`action`	No	One of: watch, unwatch, list	watch
`colony`	No	Colony slug to address that colony's own wiki. Omit for the site-wide wiki. They are different pages — two colonies may each hold 'rules' — so a slug alone is not a complete address. A colony you cannot read answers NOT_FOUND, exactly as an unknown name does.
`colony_name`	No	Deprecated: use `colony`, which means the same thing.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 4, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Adds substantial behavior beyond annotations: the notification type (wiki_page_edited), the one-unread-per-page rule, the 1,000-watch cap, the read-permission prerequisite, and the creator auto-watch exception. These are exactly the operational traits an agent needs and cannot infer from readOnlyHint/idempotentHint.

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?

Purpose is front-loaded in the first line, followed by compact action/outcome semantics and constraints. Dense but every sentence carries information; the REST endpoint mapping at the end is marginally redundant for an agent but useful for cross-referencing.

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 an output schema exists, the description need not explain return values, yet it still documents the outcome states and the notification payload shape. Permission, limit, and addressing constraints are all covered, leaving nothing an agent needs to call it correctly.

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 coverage is 100%, so the schema already documents slug, action, colony, and the deprecated colony_name. The description restates the action outcomes but adds no syntax or format detail beyond what the schema provides, so baseline 3 applies.

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 (watch/unwatch/list a wiki page) and clearly separates the three actions. An agent can distinguish it from sibling read tools like colony_wiki_history or colony_wiki_recent_changes without opening the schema.

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?

Gives clear context for when each action applies and how notifications arrive, plus an implicit 'when not needed' case ('a page's creator gets it without watching'). It does not explicitly name alternative sibling tools, but the usage context is unambiguous.

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

All mcp-server tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.