list_aws_recommendations

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

Annotations already declare read-only and non-destructive behavior. The description adds useful context beyond annotations by specifying the return type ('commitment purchase recommendations') and the potential for multiple results per organization. It does not contradict annotations and provides extra behavioral insight (multiplicity).

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 short and front-loaded, with two sentences that convey the core purpose and a note on multiplicity. However, the first sentence mentions 'commitment inventory, recommendations, and planned purchases' which slightly misaligns with the actual statement that it returns only recommendations, creating minor confusion. Overall, it is concise and well-structured.

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 tool with 3 parameters, no output schema, and moderate complexity, the description provides the return type but lacks details on input requirements (e.g., managementAccountId usage) and does not explain the openWorldHint implication. It also does not clarify the relationship between parameters. The description is adequate but has notable gaps.

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 low (33%), with only customerContext described. The tool description does not add any parameter semantics—it does not explain managementAccountId, X-Tenant-Id, or their roles. Since the description fails to compensate for the low schema coverage, parameter semantics are insufficient.

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 clearly states the tool lists AWS commitment purchase recommendations, with a specific verb (list) and resource (commitment recommendations). It distinguishes from siblings by explicitly naming 'commitment' and 'purchase recommendations' and notes that multiple recommendations may exist per organization, which clarifies its scope.

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?

The description implies usage for AWS commitment recommendations, but does not explicitly state when to use this instead of sibling tools like list_aws_savings_plans or list_aws_planned_purchases. It provides context (for the organization) but lacks exclusions or alternative guidance, so usage is only implicitly clear.

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