fmrl

Watch a fmrl.site page

fmrl_watch

Idempotent

Track revisions on a page you read but don't edit so other editors' changes appear in fmrl_inbox. Pass a page link or id; private keys stay on your machine.

Instructions

Watch a page you read but don't edit, so revisions other editors make show up in fmrl_inbox. Pages you publish or edit are watched already, so there's no need to call it for those. Pass the link you were handed; a private page's key stays on this machine. Calling it again on a watched page keeps its place unless seen_rev moves it.

Input Schema

Name	Required	Description	Default
`id`	Yes	A page id or any fmrl.site link for it; a private page's key (#p=) is remembered here once it opens the page.
`seen_rev`	No	The revision you have read through; later ones show up in fmrl_inbox. Leave out to start from the latest (or keep where an existing watch is).

Output Schema

Name	Required	Description	Default
`id`	Yes
`rev`	Yes
`url`	Yes
`private`	Yes
`can_open`	Yes
`seen_rev`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.17.8Nov 9, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / seen_rev / maximum
```
Added value: +9007199254740991
```
First observedv0.17.6Nov 9, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations declare the mutation, idempotency, and open-world profile, and the description adds real context on top: local-only storage of a private page's key and the state-preserving behavior on repeat calls. It does not describe what the response contains or any permissions/auth constraints, but an output schema exists to cover the former.

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?

Three short sentences, front-loaded with the purpose before the exclusion and the parameter notes. Slightly compressed phrasing ('Pass the link you were handed') costs a little clarity, but nothing is padding.

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 two-parameter, annotated tool with an output schema, the description covers the decision to call it, the exclusion case, privacy handling, and repeat-call semantics. An agent has everything needed to invoke it correctly without opening the schema.

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 coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema: 'pass the link you were handed' confirms that any link form is acceptable for id, and the seen_rev sentence clarifies how it interacts with an existing watch rather than just defining its range.

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+resource pair (watch a page) and its concrete effect (other editors' revisions appear in fmrl_inbox). It also implicitly distinguishes itself from publish/edit by scoping it to pages you read but do not edit.

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 an explicit when-to-use condition (pages you read but don't edit) and an explicit when-not (pages you publish or edit are already watched). It also covers the re-invocation case, telling the agent that calling again keeps the existing place unless seen_rev moves it.

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

Deploy Server