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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the trailing "Read-only" is largely redundant. The description does add the one genuinely non-structured behavioral fact: the result set includes both one-off decisions and recurring-routine outcomes. It says nothing about ordering, page size behavior, or how many records come back by default.

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?

A single front-loaded sentence with the resource first and the filters second; the parenthetical earns its place by defining the noun. The trailing "Read-only" is a minor redundancy given the annotations, slightly diluting otherwise tight structure.

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 zero-required-parameter read-only list tool with annotations covering the safety profile and no output schema, the essentials are present. It stops short of stating result ordering, default page size, or what a returned decision instance contains, which an agent would want before deciding to page through results.

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 needs to carry the param burden. It names routine_id and status as optional filters but gives no semantics for either (e.g. whether status filters to a single state), and it omits the limit parameter entirely, leaving an agent to guess that results are paginated. The self-documenting enum and default/min-max in the schema supply only partial relief.

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?

Uses a specific verb+resource ("List past decision instances") and disambiguates the noun with the parenthetical "one-off or recurring routine outcomes", so an agent knows what object is being returned. It does not distinguish itself from nearby siblings such as list_decision_prompts or list_routines, so an agent must infer that this returns outcomes rather than prompts.

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?

"Optionally filtered by routine_id or status" implies the two filtering modes, which is useful context for choosing arguments. However there is no explicit when-to-use versus when-not, and no routing to list_decision_prompts or another sibling for the prompt/question side of decisions.

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