decision_record

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds one meaningful behavioral fact — it will not infer an "accepted" status, the caller must supply it — which is real context beyond the annotations. It says nothing, however, about whether the ADR is persisted, returned inline, or what happens when status is omitted.

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 with zero padding, and the primary action is front-loaded before the caveat. Every clause carries 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?

An output schema exists, so return shape needn't be described, and the ADR framing is recognizable. But for a six-parameter, all-required tool at 0% schema coverage, the description should explain the status enum and the options minimum, which it does not — an agent can only infer them from property names.

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%, so the description must carry the burden, yet it only gestures at three of six parameters (options as "alternatives", decision, consequences) without explaining formats or limits. It never mentions title, context, or status (the only enum), and omits the structural rules the schema enforces — options require 2-10 entries, consequences up to 30.

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 ("Generate") and a specific artifact ("an ADR") plus the inputs it is built from, so the tool's function is immediately clear. It does not name or contrast any sibling, but among the review/plan tools none is close enough to be confusable, so differentiation is implicit.

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?

There is no statement of when to use this versus alternatives (e.g. implementation_plan, architecture_pattern) and no prerequisites or exclusions. "Does not invent acceptance" is a constraint on inputs, not usage routing guidance.

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