get_related_decisions

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

Annotations are entirely absent, so the description carries the full burden of behavioral disclosure. It only says what is returned, not how retrieval works, whether the operation is read-only, what 'relevant' means, or whether there are side effects or access implications.

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?

The description is a single sentence with no filler and front-loads the core noun phrase. It is appropriately terse, though the ADR acronym is unexplained and 'paths it touches' is somewhat ambiguous.

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?

The tool has an output schema, which partially covers return-value expectations, but the description lacks behavioral, usage, and parameter-interpretation context. With no annotations and only a minimal description, an agent would need to infer important details about when and how to call this tool.

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?

The schema provides 0% description coverage, so the description must compensate; it partially does by mapping 'a task' to the task parameter and 'paths it touches' to the paths parameter. It adds useful top-level semantics but does not explain parameter format, optionality behavior, or how the two parameters interact.

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 the delivered resource (ADRs and past decisions) and the relevance scope (task or paths it touches), making the tool's basic function clear beyond the tool name. It doesn't explicitly contrast with sibling tools, but the specific 'ADRs/past decisions' focus is reasonably distinct.

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 guidance on when to use this tool versus alternatives like get_task_context, read_memory, or get_domain_rules. The phrase 'relevant to a task or paths' implies a use context, but it does not state exclusions, preconditions, or what distinguishes this tool from similar memory/retrieval tools.

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