memkernel_append_decision

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

With no annotations, the description carries the full burden and does add meaningful behavior: decisions are durable, never compacted away, and re-using a key supersedes the old value while retaining it as a deprecated assumption. It omits permissions, idempotency, and whether ordering matters, but the supersede/retention semantics are genuinely non-obvious value.

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?

Three short sentences, front-loaded with the core action, and the example earns its space by disambiguating key/value syntax. No filler.

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?

An output schema exists, so return values need no explanation, and the durability/supersede model is covered. The remaining gap is the undocumented rationale parameter and no explicit sibling routing, but otherwise the agent has enough to call it correctly.

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 0% and the description compensates only partially: the example clarifies decision_key (dotted namespace, e.g. 'auth.method') and decision_value format. The required 'rationale' parameter is never explained, so one of three required inputs remains undocumented anywhere.

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 ('Record') and resource ('canonical architectural decision') scoped to 'the active branch'. It is clear what the tool does, though it never explicitly contrasts itself with close siblings like memkernel_note or memkernel_log_execution.

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: durable, never-compacted decisions suggest this is for canonical architecture choices rather than transient notes. There is no explicit 'use this instead of X when Y' routing, so the agent must infer the boundary with memkernel_note.

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