agent_memory

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

With no annotations, the description carries the full burden and largely succeeds: it discloses the store-secret model, no-account access, value/key/store size limits (64 KB, 1000 keys, 5 MB), TTL semantics (1–365 days, default 30, renewed on every write), pricing, and p99 latency. Gaps remain around error/concurrency-failure behavior and what delete permanently removes, but the operational profile is unusually rich.

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 concept and store flow before the operation enumeration and limits, so the most important content comes first. It is dense and information-rich with almost no filler, though the separate 'One price per operation' and 'Cost: $0.002 USDC per call' sentences are mildly redundant.

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 16-parameter, zero-required tool with no output schema and no annotations, the description covers the operational model, per-op semantics, limits, TTL, cost, and latency well. It stops short of explaining return shapes for get/list/search, which is a real gap given no output schema exists.

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 coverage is 63%, so some meaning must come from the description, and it adds real value: if_version for safe concurrent updates (0 = must not exist), append's oldest-items-drop behavior and max_items, incr as an atomic counter, and search matching words in keys and values. Several params (tag, prefix, limit, ttl_days, tags, with_values) get only list-level or no explicit meaning, keeping this below a 5.

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 resource ('Key-Value Store', 'Persistent memory for AI agents') and enumerates the concrete operations (set/get/get_many/delete/list/search/append/incr), so an agent knows exactly what the tool does. It is clearly distinguishable from siblings like agent_run and agent_inbox, which are unrelated capabilities.

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?

Explains the intended usage flow well: store JSON under a key and read it back in a later run or share between agents, with the first-write-creates-store lifecycle spelled out. It tells the agent which op to pick for each need (e.g. append for a rolling log/task queue, incr for counters), but offers no explicit when-not-to-use or named alternative tool.

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