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

With no annotations provided, the description carries the full behavioral burden, and it delivers two concrete traits: the operation is deterministic arithmetic with no AI involved, and unpublished inputs yield 'not_published' rather than a fabricated number. That fallback behavior is genuinely useful for an agent reasoning about trustworthiness. It does not state auth requirements or the shape of the returned value, which keeps it out of the top tier.

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?

Three sentences, front-loaded with the core action and scope, followed by the kind enumeration and the behavioral caveat. The dense kind list earns its length by mapping opaque enum values to user-facing concepts; there is no filler.

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 10-parameter tool with 1 required field, no output schema, and no annotations, the description covers purpose, kind semantics, and failure behavior adequately. The main remaining gap is that conditional parameter requirements per kind are only partially documented (in the schema descriptions, not the tool description), and the return value shape is only hinted at via 'not_published'.

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 coverage is 80%, so the baseline is 3, but the description adds real meaning beyond the schema by explaining what each 'kind' enum value means and, more importantly, which parameter family applies to which kind (e.g., taxi_minimum relates to the RTA minimum fare, salik_monthly to a commute toll). This resolves ambiguity the raw enum labels leave open. It does not document the fuel enum or the conditional requirements linking each kind to its parameters.

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 names a specific verb ('Compute') and resource ('one Dubai cost from published rates'), then enumerates all four supported cost kinds with a plain-language gloss for each. An agent immediately knows the tool's scope. It stops short of explicitly differentiating itself from the sibling get_rates, leaving that contrast to inference.

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 per-kind mapping ('taxi_minimum (RTA minimum fare)', 'salik_monthly (toll cost for a commute)') implicitly tells the agent which kind to pick for a given question. However, there is no explicit when-to-use vs get_rates, no statement of prerequisites, and no exclusions. Usage is implied rather than stated.

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