cost_report

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

With no annotations, the description carries the full behavioral burden, but it only names report content. It does not state whether the tool is read-only, whether it requires a session, what response shape to expect, or what the required `name` refers to. The phrase 'list-price estimate' hints at a non-authoritative estimate, but that is minimal.

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 compact and front-loads the domain ('journaled model calls') with no filler. However, it is a fragment and omits necessary context, so its brevity is more under-specification than effective conciseness.

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 one required parameter and no output schema, the description omits the meaning of `name` and any usage context. It names the source and two metrics, but an agent cannot reliably determine how to invoke the tool or what to expect in return.

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 0% and the description never mentions the required `name` parameter. The agent is left to guess whether `name` is a session name, a report name, or a model-call identifier.

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 identifies the resource ('cost report from the journaled model calls') and the report contents ('list-price estimate, cache hit rate'), so an agent can infer what the tool does. However, it is a noun phrase rather than a verb-headed action sentence, and it does not explicitly distinguish this tool from sibling `export_report`.

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 provides a data source ('journaled model calls') but no when-to-use guidance. It never mentions alternatives such as `query_journal` or `export_report`, nor does it state any conditions or exclusions.

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