Server Quality Checklist

Tool Scores

• memoryA
  4.8/5.0
  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 it delivers: retrieved content is explicitly 'NOT INSTRUCTION', indexing is async with jobId, search responses carry indexBuiltAt/indexStale, latest relaxes with droppedTerms, imports never overwrite and refuse credentials, and the final warning that the corpus is not current truth. It also discloses freshness field semantics and threadPosition/laterInThread so the agent knows not to treat an exchange as a conclusion.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is extremely long and dense, and while it is front-loaded with the most important caveat and uses uppercase action headers for scannability, it includes narrative examples and repeated warnings that could be trimmed (the 'failure this was built from' anecdote, the 'Measured over six real questions' walkthrough, and the closing 'silence is not evidence' restatement). The structure is logical, but the size is not concise.

  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?

  Given 14 actions and 31 parameters, the description covers everything an agent needs: action semantics, defaults, return fields, error behavior, async behavior, safety guarantees, freshness fields, and corpus organization. It even names edge cases like compaction summaries, handoff documents, and pendingIndex. With no output schema, this description is the complete reference.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Even though schema coverage is 100%, the description adds substantial meaning beyond the schema: sinceMinutes is measured against each exchange's last activity, scope supports arrays and explains widening behavior, brief preserves the envelope while trimming rows, category is required for large imports, and replace moves old versions to archive. These are operational semantics the schema alone does not convey.

  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 opens with a specific verb and resource ('Two-tier hybrid retrieval over Claude's persistent memory corpus') and then enumerates the distinct operations (search, latest, thread, sessions, verify, import, etc.). Each action is given a differentiated role, so an agent can tell them apart without opening the 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?

  Explicit routing guidance is pervasive: 'USE `latest` FOR ANY STATE QUESTION', 'Prose belongs in action: search', 'USE `thread` TO READ FORWARD FROM A HIT', and 'USE `sessions` TO SEE WHAT CONVERSATIONS EXIST AT ALL'. It also gives exclusion criteria, like preferring thread over threadLast on long threads and avoiding prose in latest because it is a literal string filter.

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