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

Annotations already cover read-only, non-destructive, closed-world behavior, and the description adds real value beyond them: the not_booked edge case and the authority boundary ('Does not approve or send. A person still decides'). It does not describe pagination or the shape of the cited numbers, but with annotations present that is a minor gap.

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 short sentences, front-loaded with what is read, followed by the fallback behavior and the limits. There is no wasted wording, though the final two clauses could be tighter.

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 one-parameter read tool with no output schema, the description covers the target fields, the not_booked case, and the non-approval boundary. The only missing element is where this fits relative to sibling read tools, which is a small gap given the tool's simplicity.

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?

There is a single parameter, caseId, and schema coverage is 100%, so the schema already documents it fully. The description adds no meaning to caseId beyond the schema, which fits the baseline of 3 when structured data does the work.

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 (read) and two named resources (originationBaseline and baselineDelta) scoped to a 'booked file', which distinguishes it from generic siblings such as read_case or read_package. It is clear what the tool returns, though the domain terms are not defined for an outside agent.

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?

'On a booked file' implies a precondition and 'Returns not_booked without a loan' implies a fallback state, so usage context is implied rather than stated. No sibling is named as the alternative when the file is not booked, and there is no explicit when-to-use statement.

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