Skip to main content
Glama
arctop

Seamless

by arctop
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

gardener_apply

DestructiveIdempotent

Resolve memory-maintenance proposals by applying, dismissing, or hiding them, settling actions like archive, merge, consolidate, split, reproject, or open follow-up tasks.

Instructions

Resolve a gardener proposal. action=apply carries out the effect (archive -> retire the memory; merge -> supersede the older by the newer; consolidate -> write a unified memory superseding its sources; digest -> save the summary as a note; reproject -> move the memory to another project; rekind -> reclassify the memory's kind in place; split -> create the child/shared projects, link the family, parent the children, retire the source; memory_wanted -> open a task to write the missing memory; tool_error -> open a task to fix the recurring error; merge_plans -> retag a stranded captured plan's notes onto the plan that holds the steps and settle the capture as merged). A proposal whose memory has gone inactive since it was raised is settled as dismissed instead, with the reason under settled. Rejecting has two strengths: action=dismiss discards this proposal and the evidence behind it, so a pattern that keeps recurring is raised again later; action=hide blocks the pattern permanently, so no recurrence re-raises it. Prefer dismiss unless the suggestion is wrong in principle rather than wrong for now. Both are reversible by the owner from the console.

Input Schema

NameRequiredDescriptionDefault
idYesproposal id (ULID)
actionNoapply (default), dismiss (until it recurs), or hide (forever)
sessionNothe session to act as: the name session_start returned, the cc/<id> or cx/<id> on your briefing's 'Seam session' line, or a session ULID. It scopes and credits this call. Defaults to this connection's session; pass it on every call when session_start reports the connection as stateless

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.4
    • addedInput schema / properties / session
      Added value: +{
+  "description": "the session to act as: the name session_start returned, the cc/<id> or cx/<id> on your briefing's 'Seam session' line, or a session ULID. It scopes and credits this call. Defaults to this connection's session; pass it on every call when session_start reports the connection as stateless",
+  "type": "string"
+}
  2. Changed2 schema fields changedv0.4.11
    • changedInput schema / properties / action / description
      Previous value: -"apply (default) or dismiss"New value: +"apply (default), dismiss (until it recurs), or hide (forever)"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "apply",
-  "dismiss"
-]New value: +[
+  "apply",
+  "dismiss",
+  "hide"
+]
  3. First observedv0.1.0

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, which covers the safety profile. The description goes further by itemizing what each apply branch destroys or rewrites (retire, supersede, parent, retag) and by stating both rejection modes are reversible by the owner from the console. It does not describe the response payload or any permission/rate constraints, so it adds real context but not a full behavioral picture.

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 and the action=apply enumeration are front-loaded and every clause carries distinct information, but the apply enumeration is a single ~150-word parenthetical run-on with semicolon-separated clauses, which makes it harder to scan than a short bulleted list would be. Sized appropriately for the decision complexity; slightly dense in presentation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and partially meets it by naming the 'settled' field and the reason recorded there. It covers the important edge cases (inactive memory, reversibility, dismiss vs hide recurrence) but does not describe the full response shape or what a successful apply returns.

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 the baseline is 3, but the description substantially enriches the action enum beyond the schema's one-line gloss by spelling out the effect of every apply sub-case, the inactive-memory override, and the permanent-vs-temporary distinction for dismiss/hide. It adds nothing for id or session beyond what the schema already states.

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 opening sentence names a specific verb+resource ('Resolve a gardener proposal') and immediately scopes it against the sibling gardener_proposals (which lists rather than resolves) and gardener_split. An agent can tell what this tool does and how it differs from its nearest siblings without opening a schema.

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?

The description explicitly guides the apply/dismiss/hide choice, including the decision rule 'Prefer dismiss unless the suggestion is wrong in principle rather than wrong for now,' and contrasts the recurrence behavior of dismiss vs hide. It also documents the fallback path when the underlying memory went inactive, so no branch is left to inference.

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