generate_decision_report

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

No annotations, so the description carries the full load. It discloses the output medium (markdown the user owns), the exact section layout, that carbon is optional, and that an audit trail with package version, catalog as_of, requester and reproduce command is embedded — genuinely useful beyond the schema. However it says nothing about whether the call is read-only vs. writes anything, whether it re-prices live or reads cached data, cost/latency, or failure behavior on incomplete workload specs.

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?

Front-loaded and mostly efficient — the first sentence names the action, format, and composition, and the section enumeration earns its space. The closing 'trust angle commercial FinOps tools can't easily replicate because their reports live in their UI' is marketing framing that adds no invocation guidance and could be cut.

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?

With no annotations and no output schema, the description usefully substitutes by enumerating the report sections an agent would otherwise have to guess. Against a 12-parameter nested workload spec with 25% coverage, though, an agent still lacks guidance on the shape and required content of the compute/storage/egress arrays needed to produce a non-degenerate report.

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% across 12 nested parameters, so the description must compensate and only partly does: it names the workload spec concept and links the schema semantics to assess_migration, and it explains that carbon is optional and requester feeds the audit trail. Egress, compute, storage, object_storage, databases, commitment, one_time and multi_az receive no explanation, leaving the agent to infer nested element shapes from the sibling tool.

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?

States a specific verb and resource ('Generate a CFO-grade FinOps decision report in markdown') and explicitly positions it as a composition of two named siblings, assess_migration and compare_carbon_footprint. An agent can distinguish this from compare_clouds or compare_total_cost_of_ownership without opening any schema.

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?

Gives an explicit triggering question ('we need a decision artifact a CFO can sign off on') and names the underlying tools it wraps, which implies the alternative of calling those directly for raw numbers. No explicit when-not-to-use or cost/latency caveat, so it stops short of a 5.

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