amem_usage_report

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

With no annotations, the description carries the burden and does well: it discloses that amem computes the saving server-side from real file sizes, so the agent should not estimate, and that paths not in the packet are ignored. It does not state whether this is a write/attestation that persists, what happens on a repeat call, or what the tool returns, which is a meaningful residual gap for an unattested mutation.

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 purpose and the timing constraint in the first two sentences, with the anti-estimation warning early. It is somewhat padded — the closing reassurance and the restated parameter names duplicate schema fields — but nothing is confusing or out of order.

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 four-parameter tool with no output schema and no annotations, the description covers the critical decision points: when to call, what to report, what not to compute, and the omission default. The main missing piece is the return value — with no output schema, an agent cannot know whether it gets back a saving figure or an acknowledgement.

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 75%, so the schema already documents most fields; the description adds real semantic value by clarifying that anchors_opened means anchors you ended up opening anyway rather than a token estimate, and by explaining the intent of answered. event_id and workspace are left entirely to the schema, so it is not a full 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?

The description states a specific verb and resource — report what you did with the last amem context packet — and frames the outcome (its savings estimate becomes a measurement). That framing alone distinguishes it from retrieval siblings like amem_context or amem_stats, which produce the packet or aggregate numbers rather than attest usage.

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?

Timing is explicit: "Call this once after you have finished acting on a packet," and there is a clear prohibition ("Do NOT estimate tokens"). It also pre-empts a likely withholding behavior by saying reporting that you opened everything is expected. It does not name a sibling alternative or say when not to call it at all (e.g., if no packet was ever issued), which keeps it below a 5.

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