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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. Beyond that, the description adds useful behavior: results are 'newest first', amounts owed are broken out 'per currency', and the person filter admits only one value ('person keeps to one') – details not present in the structured fields.

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 a single dense sentence that front-loads the resource definition. It is efficient, though phrases like 'person keeps to one' and the trailing 'Free' are terse enough to risk ambiguity.

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 output schema and four undocumented-in-schema parameters, the description covers status semantics, ordering, and per-currency amounts but omits pagination (limit/offset) and any hint of the returned fields. It is adequate but leaves real gaps for an agent configuring the call.

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 0%, so the description must carry parameter meaning. It explains the status enum values and their default and hints the person filter is single-valued, but says nothing about limit or offset, leaving pagination undocumented in both schema and description.

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 clearly defines the resource ('expense claims: what people paid for the business with their own money') and the statuses it can list, so an agent can tell this is a read/list operation over claims. It does not explicitly name its mutation sibling books_repay_claims, so differentiation relies on the resource wording rather than routing guidance.

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?

It signals the default status ('still to repay (the default)'), which is useful context for invocation, but it never states when to use this versus alternatives like books_repay_claims or books_record_expense. Usage is implied rather than guided.

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