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

Annotations already declare readOnly/ idempotent / non-destructive, so the safety profile is covered elsewhere. The description adds one genuinely new behavior: default ordering is newest first. It says nothing about pagination behavior (limit max 100, offset-based paging) or result size, which is relevant for a list tool.

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?

A single tight clause plus a routing pointer, with the key scoping fact ('newest first') front-loaded. No filler or restatement of the title.

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 7 parameters, the description should say at least what a receipt row contains or how paging behaves. As written, an agent knows what the tool lists and the default order but must open the schema for filtering and gets no hint about returned fields.

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 57%; search, status, and date params are documented in-schema, while sort/limit/offset are self-evident enums/defaults. The description adds only the 'newest first' default for sort, not enough to exceed the baseline for a partially documented schema.

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?

States a specific verb+resource and disambiguates what a receipt is ('Payments made to Pirate Ship'), which an agent could not infer from the name alone. It also names the sibling get_receipt for single-record retrieval, separating the list and get cases.

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 clause 'get_receipt shows one' implicitly tells the agent to use this tool for lists and the sibling for a single record, which is useful directional guidance. However, there is no guidance on when to choose this over adjacent tools like list_transactions, list_refunds, or export_report, which also surface payment data.

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