buzz_save

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

Annotations only say this is a non-read-only, idempotent, non-destructive write; the description goes well past that by disclosing the default privacy posture ('Private by default (NIP-44 encrypted to you)'), the exact opt-out that makes data public, and the reason for the agent-mode restriction ('kind 10003 isn't on Ekam's wire-sign allowlist'). That privacy default is the single most consequential fact about this tool and it is front and center, with nothing contradicting the annotations.

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?

Four short clauses, purpose first, then privacy default, then the inverse operation, then the environment caveat — nothing is repeated and every clause changes how an agent would call the tool. Even the parenthetical jargon (kind 10003, wire-sign allowlist) is doing real work by explaining the restriction.

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 5-parameter write tool with no output schema, the description covers purpose, privacy default, unsave path, and environment limits — enough to call it correctly. It is silent on what a successful save returns or whether re-saving an already-saved message is a no-op versus an error, which is the one gap an agent might hit in practice.

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 100%, so the schema already documents all five parameters, including the private default and the remove toggle. The description's restatement ('private: false makes the entry public', 'remove: true unsaves it') adds a little framing but no syntax or edge-case detail beyond the schema, and dry_run is not mentioned at all. Baseline 3 is the right call when the schema carries the semantics.

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 ('Save a message for later') and grounds it in a concrete mental model ('like Slack's Saved items') plus the underlying storage ('your NIP-51 bookmark list (kind 10003)'). That distinguishes it cleanly from siblings like buzz_saved (the listing counterpart) and buzz_react/buzz_remind, which touch the same message but do different things.

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?

The description makes the save/unsave toggle explicit via 'remove: true unsaves it', so an agent knows the inverse operation lives here rather than in a separate delete tool. It also gives a hard usage precondition ('Agent mode only for now'). It never names buzz_saved as the read-side alternative, which keeps it short of a full 5.

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