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

The readOnlyHint and destructiveHint annotations already tell the agent this is a safe read, so that part of the behavior is covered. However, the description adds nothing beyond 'lists' and does not say whether result sets are paginated, whether filters are applied automatically, whether it can return partial data, or what a zero-result list looks like. The absence of an output schema makes this gap more significant.

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 efficient sentence and contains no filler words. However, the brevity is borderline description-by-name and no additional structured information is front-loaded. It earns a middling score because conciseness without content is under-specification, not compactness.

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 8 parameters and no output schema, the description is far too terse to give an agent a complete operational picture. It mentions neither querying behavior nor required connection context, and the sibling list alone does not show when to choose this tool over brc_batch_purchases. The implementation is missing both return-format and failure-mode context, so an agent may call it correctly only because the schema happens to require companyName.

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?

The input schema documents companyName, filter, orderBy, and connectionRef, but top/page/skip/pageSize are unannotated and the description does not clarify their semantics. Since schema description coverage is only 50%, the description was expected to compensate, but it introduces no meaning for any parameter. It does not explain how pagination params interact or what a valid companyName looks like beyond the schema example.

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 and resource: it 'lists' 'BRC purchases,' so an agent can tell this returns purchase-related records. It is distinct from nearby get- and batch- tools, though it doesn't explicitly say how it differs from brc_list_purchases or brc_batch_purchases. The one-sentence description is clear, but I would be slightly clearer about what a 'purchase' record contains.

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?

There is no guidance on when to use this tool versus a related tool such as brc_get_purchase or brc_batch_purchases. It does not mention prerequisites like verifying an active company context or deciding between listing and retrieval. An agent is left to infer all usage contexts from the schema and sibling list.

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