memory_record

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

With no annotations the description carries the full burden and largely delivers: it explains that `supersedes` targets stop surfacing in search/recall but remain readable by id, that credentials/card numbers are mechanically redacted, that `resolves`/`corrects` are written to a lifecycle ledger, and what the response contains (`thread_ids`). It omits permissions, reversibility, and any failure/conflict behavior, so not a 5.

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

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

Front-loaded with the core action before the detail, and each sentence carries distinct information about a distinct parameter or behavior. It is dense and somewhat long, but there is little filler; backticked parameter names aid scanning.

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

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

For a 10-parameter mutation tool with no annotations and no output schema, the description explains response `thread_ids` reasonably well, but five parameters (files, decisions, open_threads, agent, session_id) receive no guidance at all, and there is no mention of permissions or conflict behavior. Adequate but with clear gaps.

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

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

Schema description coverage is 0%, so the description must compensate. It richly documents `summary` (one line, ≤500 chars), `details`, `supersedes`, `resolves` (including the `<record-id>#<n>`, record-id, and `vault:<id>` forms), and `corrects` (with a target/claimed/truth/evidence shape), but leaves `agent`, `files`, `session_id`, `decisions`, and `open_threads` entirely undocumented — half the parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — persist a completed unit of work into ASM memory and the Obsidian daily log — and the trigger ('Call after changing files'). Clearly distinguished from the read-side siblings (brain_search, memory_recent) without needing to open any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Gives explicit context for use ('call after changing files') plus content rules: record concrete outcomes and unresolved work, never secrets/credentials/raw transcripts/unverified claims. It stops short of naming alternatives or exclusions (e.g., when to prefer memory_recent or brain_search), so it is clear but not fully routing.

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