Skip to main content
Glama
anaknegeri

agent-session

by anaknegeri
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

memory.put

Save long-term project facts, architecture choices, fixes, or preferences as indexed memory entries for later retrieval. Search first to avoid duplicates; each call creates a new ID.

Instructions

Save one piece of long-term knowledge that outlives the session — a fact about the project, an architecture choice, a fix that worked, a user preference — and index it for memory.search; context.get surfaces related entries later. Every call adds a new entry with a new ID (nothing is merged or overwritten), so memory.search first to avoid a duplicate. Works without an active session. Returns the entry JSON with its id; errors on an unknown kind. To copy this session's decisions, resolved blockers and completed tasks in bulk use memory.promote.

Input Schema

NameRequiredDescriptionDefault
kindYesproject_knowledge (facts about the codebase), architecture (design choices), solution (a fix that worked), preference (how the user wants things done), or skill (a reusable procedure)
contentYesSelf-contained plain text a future agent can act on without this session, e.g. "The billing API rejects requests without an Idempotency-Key header"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.10
    • changedInput schema / properties / content / description
      Previous value: -"The knowledge to remember"New value: +"Self-contained plain text a future agent can act on without this session, e.g. \"The billing API rejects requests without an Idempotency-Key header\""
    • changedInput schema / properties / kind / description
      Previous value: -"project_knowledge|architecture|solution|preference|skill"New value: +"project_knowledge (facts about the codebase), architecture (design choices), solution (a fix that worked), preference (how the user wants things done), or skill (a reusable procedure)"
  2. First observedv0.1.8

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses append-only semantics ('Every call adds a new entry with a new ID (nothing is merged or overwritten)'), the error condition ('errors on an unknown kind'), the return shape ('the entry JSON with its id'), and that no active session is required.

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?

Front-loaded with the verb and resource, then behavior, then the sibling alternative — a sensible ordering with no filler sentences. It is dense for a two-parameter tool, with the first sentence carrying a long em-dash aside, but every clause still carries information.

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?

No output schema exists, yet the description states what comes back (the entry JSON with its id) and what fails (unknown kind), plus the append-only behavior that determines whether a caller must dedupe first. Nothing an agent needs to call it correctly is missing.

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 adds meaning by tying each save to a kind category and by characterizing what good content looks like (a self-contained fact, an architecture choice, a fix that worked, a user preference). It stops short of adding syntax or format detail beyond the schema's own examples.

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: 'Save one piece of long-term knowledge that outlives the session', with concrete examples of what counts as an entry. It also names a sibling (memory.search) as the index target and memory.promote as the bulk alternative, so the agent can tell it apart from neighbors.

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?

Explicit conditional guidance: 'memory.search first to avoid a duplicate' and 'To copy this session's decisions, resolved blockers and completed tasks in bulk use memory.promote.' It also states a positive precondition that lifts a common restriction ('Works without an active session').

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