Decision memory

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the mutation/idempotency profile is covered structurally. The description adds only the notion of 'supersede' (implying the prior decision is retained rather than deleted), but says nothing about persistence scope, permissions, or what happens to state on update/supersede beyond that inference.

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?

Two sentences, no redundancy: the first front-loads the action set and resource, the second front-loads the trigger condition. Every word earns its place.

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 20-parameter, five-action tool this is thin. The description lists only four actions and omits check_alignment entirely, which is exactly where it collides with the sibling check_decision_alignment tool, and it gives no indication of what list/record returns (no output schema exists to compensate).

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 100% and every one of the 20 parameters carries its own inline '(for <action>)' hint, so the schema does the heavy lifting. The description adds no per-parameter meaning beyond what the enum documentation already supplies, so the baseline of 3 applies.

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 names specific verbs (record, list, update, supersede) tied to a concrete resource (the developer's architectural and tech decisions), so the tool's function is unambiguous. It does not explicitly differentiate itself from the overlapping siblings check_decision_alignment or agent_memory, which keeps it out of 5 territory.

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?

A clear triggering condition is given: 'Call when the user makes, changes, or asks about a settled decision or convention.' That covers the main invocation contexts, but there is no when-not guidance and no routing advice against the sibling check_decision_alignment tool even though this tool also exposes a check_alignment action.

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