list_aws_organizations

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

Annotations indicate readOnlyHint=true and destructiveHint=false, which the description aligns with—no contradictory behavior is asserted. The description adds substantial behavioral context beyond annotations: it details the output shape (metadata, trailing 30-day stats, precomputed savings totals, monthlyPotentialSavings), explains the pagination behavior, and notes the attention to client-side aggregation. It also implicitly warns about the complexity of the response, clarifying expectations.

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 long but information-dense, with every sentence serving a purpose: explaining the API's context, the response's rich structure, and the exact pagination protocol. It's front-loaded with the essential purpose and then adds details in a logical order. No fluff or redundancy.

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?

Despite the lack of an output schema, the description explicitly enumerates the key fields (monthlyPotentialSavings, savings totals per SP type) and outlines the pagination contract. Given the tool's moderate complexity with 4 parameters and no output schema, it provides enough for the agent to correctly invoke and interpret results. It could briefly mention whether the response is an array or object, but that's minor.

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 only 25% (only customerContext has inline description). The description mentions pagination and pageToken in context, which adds meaning to that parameter, and maxResults is clear from its name and bounds. However, it doesn't elaborate on X-Tenant-Id or customerContext beyond what the schema says, and the general parameter semantics for pagination are only partially explained (no mention of maxResults defaults or limits). Since the description covers the core pagination behavior but leaves other parameters to the schema, a 3 is fair.

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 that this tool returns all AWS Organizations accessible to the authenticated tenant, and explicitly frames it as part of 'PerfectScale for Commitments (AWS)' covering commitment inventory, recommendations, and planned purchases. This unambiguous verb-resource pairing (list → AWS Organizations) distinguishes it from siblings like list_aws_member_accounts or list_organizations.

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 explains the pagination workflow (call again with the returned pageToken until no pageToken appears), which is a usage-critical instruction. While it doesn't explicitly mention alternatives, the tool's specific scope (commitments context) and the statement 'Returns all AWS Organizations' naturally imply when to use it vs. siblings. It lacks explicit when-not-to-use guidance, but the context is clear.

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