OmniFocus MCP Plus

Overview Schema Source Related Servers Discussions Admin

Update perspective rules

update_perspective_rules

Destructive

Replace a custom perspective's filter rules and optional aggregation in OmniFocus. Validates criteria before writing, verifies the change with rollback, and returns previous rules for easy undo.

Instructions

Replace a custom perspective's filter rules (and optionally its aggregation). Overwrites — read current rules first via list_custom_perspectives includeRules. Keys are validated before writing (OmniFocus silently accepts invalid rules), the write is read-back verified with rollback, and the previous rules are returned for undo.

Input Schema

TableJSON Schema

Name	Required	Description
`rules`	Yes	The COMPLETE replacement rule array — this overwrites the perspective's rules, it does not merge. Read the current value with list_custom_perspectives({includeRules: true}) first. Leaf rules use keys such as: actionAvailability, actionStatus, actionHasDuration, actionWithinDuration, actionIsUntagged, actionHasTagWithStatus, actionHasAnyOfTags, actionHasAllOfTags, actionHasNoProject, actionHasProjectWithStatus, actionIsInSingleActionsList, actionWithinFocus, … Nest with { aggregateRules: [...], aggregateType: 'all' \| 'any' \| 'none' } and disable a clause with { disabledRule: {...} }. Example: [{ actionAvailability: 'remaining' }, { aggregateRules: [{ actionStatus: 'flagged' }, { actionStatus: 'due' }], aggregateType: 'any' }]
`aggregation`	No	Top-level filter aggregation: 'all' = every rule must match, 'any' = at least one. Pass null to clear it. Omit to leave the perspective's current aggregation untouched.
`perspectiveId`	No	Identifier of the custom perspective (from list_custom_perspectives). Takes precedence over perspectiveName.
`perspectiveName`	No	Name of the custom perspective to rewrite. Ambiguous names are rejected with the matching identifiers — use perspectiveId then.
`allowUnknownKeys`	No	Write rule keys this tool does not recognize. Default false. OmniFocus silently ignores unknown keys, which can turn a narrow perspective into one that matches everything — only set this if you are certain the key is valid for your OmniFocus version.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`meta`	No
`tool`	Yes
`success`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.0Sep 15, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the destructiveHint annotation, the description discloses that keys are validated before writing because OmniFocus silently accepts invalid rules, that the write is read-back verified with rollback, and that previous rules are returned for undo. This gives an agent confidence and a recovery path. It clearly describes the mutation and its safeguards.

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?

Two compact sentences lead with the core operation, then immediately flag the overwrite behavior, then pack in validation, rollback, and undo value. No filler or repetition of schema content.

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?

The description covers the destructive nature, prerequisite read, validation/rollback safeguards, and undo output, while the schema supplies parameter specifics and the output schema covers the return shape. Nothing an agent needs to invoke this safely is missing.

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 100%, so the schema already documents all five parameters, including the complete-replacement semantics of rules and the allowed aggregation values. The description reinforces that the operation optionally writes aggregation and says to read current rules first, but doesn't add parameter-level detail beyond the schema. Baseline 3 is appropriate.

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?

Description opens with a specific verb and resource: 'Replace a custom perspective's filter rules' and explicitly notes optional aggregation. It self-identifies as overwriting rather than merging, so an agent can distinguish it from read-only perspective tools like list_custom_perspectives. No ambiguity remains.

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 preconditions: 'read current rules first via list_custom_perspectives includeRules' and explains that the tool overwrites. It doesn't state exclusions or name an alternative for the same write operation, but no sibling provides this exact update capability, so the context is sufficient.

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

Deploy Server