Report Decision

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

The annotations only say readOnlyHint=false, so the key behavioral fact here — that the result is a draft requiring human review rather than a published record — is genuinely additive and important. However, the description says nothing about permissions, whether repeated calls create duplicates, or what the caller receives back (an ADR id? a link?).

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 short sentences, zero filler, and the action is front-loaded ahead of the consequence (draft ADR pending review). Nothing could be removed without losing information.

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 mutation with a fully documented schema and a safety annotation, the description covers what the tool does and the review-gated outcome. The remaining gap is the return value and duplicate-handling, which is a modest omission rather than a blocking one.

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 each of the five fields carries its own example-rich description, so the schema already does the semantic work. The tool description adds no extra meaning about what belongs in context vs. decision, so baseline 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?

"Record an architecture decision" gives a specific verb and resource, and the second sentence clarifies that it produces a draft ADR in SystemDox. That is clearly distinct from every sibling (the get_* family and the create_check / create_guardrail / create_project_rule writers), though the description never names an alternative to reinforce the contrast.

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?

"Made during development" and "for human review" imply the moment to call it, but there is no explicit when-not guidance, no prerequisites (does the project need to be linked first?), and no mention of an alternative path such as just discussing the decision in chat.

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