Skip to main content
Glama

Povver — Strength Training

Read Memory

read_memory
Read-only

What the user asked Povver to remember. view: list (category injury|health|preference|goal|personal, status, limit up to 200: default: active and monitoring memories, which gate training) · detail (memory_id: status history, severity, body_area) · suppressions (limit up to 50: progressions held back by an injury memory, with that memory). Change them with manage_memory.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "view": "<view>"
    },
    "name": "read_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewYes
limitNolist: 1-200 (default 50). suppressions: 1-50 (default 10).
statusNo
categoryNo
memory_idNodetail: the memory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / category / enum
      Previous value: -[
      -  "injury",
      -  "preference",
      -  "goal",
      -  "personal"
      -]New value: +[
      +  "injury",
      +  "health",
      +  "preference",
      +  "goal",
      +  "personal"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (1-100)."New value: +"list: 1-200 (default 50). suppressions: 1-50 (default 10)."
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +200
  3. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description instead adds the non-obvious default that list returns "active and monitoring memories, which gate training" and that suppressions surfaces held-back progressions. That is genuinely useful behavior not derivable from the schema. It does not state ordering, pagination of beyond-limit results, or whether resolved memories are excluded by default in suppressions.

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?

The purpose is front-loaded in the first sentence and the rest is a dense, view-by-view enumeration with no filler. The telegraphic "·"-separated style occasionally drops verbs (e.g. the meaning of "default: active and monitoring" is inferred rather than stated), costing a little clarity, but nothing is redundant.

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?

For a five-parameter read tool with no output schema, the description adequately previews what each view yields (status history, severity, body_area; held-back progressions) so the agent can pick a view before calling. Missing are return ordering/shape beyond the field hints and confirmation of whether suppressions respects the status filter.

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?

With only 40% schema description coverage, the description carries real load: it tells the agent which parameters belong to which view (category/status/limit for list, memory_id for detail, limit for suppressions) and caps limits at 200 and 50 respectively. It adds the default status behavior, which the schema does not state. It is written in a compressed shorthand, though, so the mapping of limit defaults per view is left slightly ambiguous.

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?

Opens by stating the resource in domain terms ("What the user asked Povver to remember") and enumerates the three read modes with the data each returns. It also names the sibling that mutates the same resource ("Change them with manage_memory"), so an agent can separate it from manage_memory 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Each view is given a selection criterion by describing its payload: list for filtered browsing, detail for a single memory's status history/severity/body_area, suppressions for progressions held back by an injury memory. The write alternative is explicitly routed to manage_memory. It stops short of stating exclusions such as which view to prefer when you already have a memory_id or when suppressions data is meaningless without an injury memory.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.