catalog_search

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the agent knows this is a safe, read-only operation with an open world (results may change). The description adds the 'bounded page' behavior and the 'selecting approved line items' purpose, which are useful. However, it does not disclose details like whether the catalog is filtered by default, how 'approved' is determined, or what happens when the cursor is invalid. With annotations covering the safety profile, a 3 is appropriate.

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, concise sentence that front-loads the core action ('List a bounded page') and includes the purpose ('for selecting approved line items'). Every word earns its place; no filler or repetition of schema details.

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 read-only paginated list tool with no output schema, the description is adequate but not complete. It tells the agent the tool lists a bounded page of catalog items, but it does not describe the return shape (beyond the schema's next_cursor and returned_so_far hints), nor does it explain how 'approved' is determined or how to handle empty results. Given the openWorldHint and readOnlyHint annotations, the safety profile is covered, but the operational details are thin.

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 67%: cursor and returned_so_far have descriptions, while page_size has only a default and min/max. The description adds the concept of a 'bounded page' and 'selecting approved line items', which gives some context for why pagination exists. However, it does not explain the relationship between returned_so_far and cursor beyond what the schema already says, nor does it clarify the meaning of 'approved' in relation to parameters. Baseline 3 is fair since the schema covers most parameter semantics.

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 ('List'), a resource ('Jobber products and services'), and a scope ('bounded page', 'for selecting approved line items'). It is clear about what the tool does, though it does not explicitly differentiate from sibling tools like search_records or get_record. The phrase 'for selecting approved line items' adds useful context about its intended use.

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 implies usage context: it is for browsing a bounded page of catalog items, likely for selection workflows. However, it does not explicitly state when to use this tool versus alternatives like search_records or get_record, nor does it mention any exclusions or prerequisites. The pagination parameters imply iterative usage, but the description itself does not guide the agent on when to choose this tool over siblings.

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