memkernel_post_notice

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

With no annotations, the description carries the whole burden and does so well: it discloses cross-branch visibility, survival across rollback and GC, TTL causing staleness rather than deletion, the need for explicit clearing, and that no lock is acquired (distinguishing it from the lease family). It stops short of stating whether re-posting the same resource replaces or duplicates, and what permissions or auth are needed.

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 sentences, front-loaded with the core action and example, then escalating to lifecycle behavior. No padding, though the trailing 'No lock is acquired' reads as an isolated fragment that could be folded into a clearer contrast sentence.

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 3-param mutation tool with an output schema (so return values needn't be described), the description covers the lifecycle and durability semantics that an agent cannot infer elsewhere. The remaining gap is conflict/idempotency behavior on repeated posts to the same resource, plus the undocumented TTL parameter.

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% across 3 params, so the description must compensate and largely doesn't. The example conveys a colon-namespaced convention for `resource` and hints that `message` is the advisory text, but `ttl_seconds` (default 3600) is never mentioned in the description, nor is its unit or effect on staleness timing.

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 — 'Post a workspace-wide advisory' — and the inline example ('service:auth / changing login') makes the concept concrete. It implicitly distinguishes itself from lease/decision siblings by being an advisory rather than a lock or a durable record, but it never names a sibling to contrast with.

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?

Usage is implied rather than stated: the reader infers 'use this to broadcast a transient warning to all workers'. The line 'Clear it explicitly when done' gestures at memkernel_clear_notice without naming it, and there is no guidance on when an advisory beats memkernel_append_decision or memkernel_note.

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