Skip to main content
Glama
phasespace-labs

palinode

by phasespace-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

palinode_correction_preview

Read-onlyIdempotent

Preview what correcting or retiring a memory would change without writing anything, and get the revision required by palinode_correction_apply so later edits are refused, not merged.

Instructions

Show exactly what correcting or retiring one memory would change — and change nothing. Returns the old text, the proposed new text, the affected document (and claim), its exact source revision, the rationale, where the correction came from, the project scope, the supersedes/superseded_by relation that would be recorded, every other record that quotes or derives from the target (reported, never rewritten), and the recovery command. Call this before palinode_correction_apply: the revision it returns is what apply requires back, so a target that changed in between is refused rather than silently merged.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionNosupersede (a replacement stands) or retire (nothing does). Derived from `replacement` when omitted.
reasonNoWhy. Recorded in the history sibling and the commit subject.
targetNoMemory to correct: 'decisions/x.md', 'decisions/x', or a bare slug. A slug naming two memories is refused with both, never guessed.
projectNoProject scope. Inferred from the target's own entities when omitted.
claim_idNoNarrow the correction to one '<!-- fact:id -->' claim inside the target.
backed_byNoRecords supporting the REPLACEMENT (category/slug refs). The superseded original is never cited as support for its replacement — it is lineage, and a verified quote of it establishes what it said, not that the new claim is true.
replacementNoThe text that would stand instead. Omit to retire the target with no successor.
candidate_idNoThe palinode_corrections candidate this came from; its span, session and turn become the recorded source.
allow_content_lossNoExplicitly permit dropping the original text listed by preview.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.22.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is lower; the description clears it easily by disclosing the return payload, the revision-token contract with apply, and the concurrency guarantee (stale targets refused, never silently merged). It also notes quoting records are 'reported, never rewritten', which is real behavioral context.

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?

Purpose and the must-call-before-apply rule are front-loaded, and the long return enumeration is justified because no output schema exists. Every clause carries distinct information; none is 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?

With no output schema and 9 parameters, the description carries the burden and does so: it enumerates the return contents, the revision contract, and the stale-target refusal behavior. An agent has everything needed to call it correctly on the first attempt.

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% and every parameter carries a detailed inline description, so the schema already does the heavy lifting. The description echoes return fields (rationale, source, project scope, supersedes relation) but adds no syntax or format detail beyond what the schema provides. 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?

States a specific verb and resource ('Show what correcting or retiring one memory would change') plus the critical scope constraint ('and change nothing'), which distinguishes it from the mutating sibling palinode_correction_apply. An agent can tell it apart from the apply tool without opening either 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?

Explicitly says 'Call this before palinode_correction_apply' and explains why: the revision it returns is required by apply, so a target changed in between is refused rather than silently merged. This gives both the when and the consequence, leaving nothing 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