Skip to main content
Glama
soil-dev

capsulemcp

by soil-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

run_saved_filter

Read-only

Retrieve paginated results from a saved Capsule filter by its ID. Leverages pre-configured sorting to answer 'most recent' queries in one call; find filters with list_saved_filters first.

Instructions

Run a saved filter by id and return its results, paginated. Unlike filter_parties / filter_opportunities / filter_projects (which use the ad-hoc filter endpoint and CANNOT sort), saved filters DO support sort — the orderBy is configured in Capsule's web UI when the filter is created. So 'most recent X by Y' questions are answerable in one call IF a saved filter exists; use list_saved_filters first to find one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesThe saved filter id (from list_saved_filters).
pageNo
embedNoComma-separated embeds. Valid tokens depend on entity — parties: tags, fields, organisation, missingImportantFields; opportunities: tags, fields, party, milestone, missingImportantFields; projects: tags, fields, party, opportunity, missingImportantFields.
entityYesWhich entity type the filter operates over.
perPageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.0
    • changedInput schema / required
      Previous value: -[
-  "entity"
-]New value: +[
+  "entity",
+  "id"
+]
  2. Changed1 schema field changedv2.2.0
    • changedInput schema / properties / embed / description
      Previous value: -"Comma-separated embeds. Valid tokens: tags, fields, missingImportantFields."New value: +"Comma-separated embeds. Valid tokens depend on entity — parties: tags, fields, organisation, missingImportantFields; opportunities: tags, fields, party, milestone, missingImportantFields; projects: tags, fields, party, opportunity, missingImportantFields."
  3. Changed3 schema fields changedv2.1.2
    • changedInput schema / properties / embed / description
      Previous value: -"Comma-separated embeds, e.g. 'tags,fields'"New value: +"Comma-separated embeds. Valid tokens: tags, fields, missingImportantFields."
    • changedInput schema / properties / entity / description
      Previous value: -"Which entity type the filter operates over. Use 'kases' for projects (Capsule's legacy name)."New value: +"Which entity type the filter operates over."
    • changedInput schema / properties / entity / enum
      Previous value: -[
-  "parties",
-  "opportunities",
-  "kases"
-]New value: +[
+  "parties",
+  "opportunities",
+  "projects"
+]
  4. Addedv1.7.0
  5. Removedv1.6.2
  6. First observedv1.0.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already signal readOnly/destructive safety; the description adds important behavior beyond that: results are paginated, saved filters support sort with orderBy fixed in the web UI, and the one-call shortcut only works if a saved filter exists. No contradictions with annotations.

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?

The description is front-loaded with the core operation, then adds a crisp distinction and a concrete use case. Every sentence earns its place; no filler.

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 read-only filter tool, it covers purpose, pagination, sorting caveat, and prerequisite discovery via list_saved_filters. Combined with the schema's param constraints and default values, an agent has enough to select and invoke the tool 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?

The schema covers id, entity, and embed with descriptions; page and perPage rely on names/defaults/constraints. The description adds key id provenance ('from list_saved_filters') and pagination context, but does not explain page/perPage values beyond what the schema already conveys.

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 names a specific action ('Run a saved filter by id'), the resource ('saved filter'), and the output ('return its results, paginated'). It also explicitly distinguishes itself from filter_parties/filter_opportunities/filter_projects, so an agent can tell it apart without inspecting schemas.

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?

It gives precise usage context: use saved filters when sort is needed because the ad-hoc filter endpoint cannot sort, and use list_saved_filters first to find the id. This directly answers when-to-use versus alternatives.

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

Deploy Server

Other Tools