Action Status

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

Annotations already declare readOnlyHint=true, so the tool is known to be safe. The description adds valuable behavioral context by interpreting statuses (e.g., 'needs_review means it ran but the outcome could not be confirmed', 'unknown means the provider MAY have acted - never re-propose the same action'), going beyond what annotations provide. No contradictions.

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 covering purpose, status list, and usage guidance. Front-loaded with key information. No redundant or irrelevant content.

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?

Given one fully documented parameter, no output schema, and no nested objects, the description provides all necessary context: what the tool does, when to use it, and how to interpret results. Status semantics are explained clearly.

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 single parameter 'action_id' has schema description 'ID returned by action_propose'. With 100% schema coverage, the description adds minimal additional value but does clarify the source of the ID, which is helpful context. Baseline 3 is appropriate.

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 states 'Check the status and outcome of an action' with a specific list of status values (proposed, awaiting_confirmation, etc.), clearly defining the tool's purpose and distinguishing it from sibling tools like action_commit and action_propose.

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?

Explicitly states 'Use after action_commit to see whether the patient has approved yet' and provides conditional guidance for 'needs_review' and 'unknown' statuses, including what actions to take (show evidence, never re-propose).

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