reprice_bill

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

With no annotations, the description does real behavioral work: it discloses that processing is local and 'nothing is sent anywhere', that the basis is list price (not discounted), and that unpriceable lines (GPUs, licensed OS, unknown types) are reported with their cost rather than silently dropped. It does not mention runtime, file size limits, or permissions, which keeps it from a 5.

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 first sentence front-loads what the tool does, followed by the pricing scope and the exclusions, then the example queries. It is dense and mostly earns its words, though the middle sentence is long and could be split for faster scanning.

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?

There is no output schema, and the description compensates by describing the return shape: per-instance-type and total figures across four clouds, alongside actual paid, plus an unrepriceable-items section. For a two-parameter analysis tool with no annotations this is close to sufficient; only limits and runtime behavior are absent.

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 100%, so both parameters are already documented in the schema and the baseline applies. The description adds only incidental meaning about file_path (a FOCUS 1.x CSV export) and says nothing about top_n's role as a truncation control on workload lines.

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 a specific verb and resource ('reprice' the user's actual bill), names the input format (local FOCUS 1.x CSV), and names the output shape (list price on AWS/Azure/GCP/OCI per instance type and in total, next to what was paid). That is enough to distinguish it from the catalog-lookup siblings like get_aws_price or compare_clouds.

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?

Three concrete 'Use for' triggers are given ('what would our bill cost on another cloud', 'are we on the cheapest cloud', 'is a migration worth looking at'), making the when-to-use case clear. It never names an alternative tool or states when not to use it, so it stops short of full routing guidance.

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