smokeball_get_matter_items

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description aligns with this by requiring the effect to be 'read'. The description adds the governance constraint that the operation routes only through the exact project/account governed connector authority, which is useful behavioral context beyond the annotations. It also notes that Spring verifies the effect, adding a small non-obvious detail.

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 relatively compact and uses a bulleted parameter list, which is easy to scan. The top line names the operation, and the governance routing note is front-loaded. However, the parameter list items are mostly restatements of the schema and add little value; the whole block could be more concise if the parameters were aggregated into a single sentence of meaningful guidance.

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?

The tool has an output schema, so return values need not be described. The annotations cover read-only/idempotent behavior. However, the description does not explain how to construct the 'arguments' JSON string, what matter items actually are in Smokeball terms, or how the combination of project_id/project_ref/connector_account_ref is used for routing. For a connector operation with seven parameters and no schema descriptions, this feels incomplete for an agent that needs to make a correct first 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 description coverage is 0%, and the description simply lists parameter names without explaining their types or formats. It does say the 'arguments' is a JSON string and that 'effect' must be 'read', but it fails to clarify what project_id, project_ref, connector_account_ref, idempotency_key, and approval_ref mean, what the JSON structure for 'arguments' should be, or which are required/optional beyond the schema's required field. The description does not compensate for the lack of schema descriptions.

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 identifies the operation as 'get_matter_items' and lists it as a Smokeball connector operation, which clearly indicates a read/listing of matter items. However, it does not explicitly state what 'matter items' are (e.g., files, tasks, time entries, contacts) or what the tool returns, leaving some ambiguity. It is distinguishable from sibling tools like smokeball_get_matter by the 'items' suffix, but the description lacks a plain-language statement of what items are retrieved.

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 provides routing context ('Routes only through the exact project/account governed connector authority') and implies this is a read operation, but it does not explicitly state when to use this tool versus alternatives like smokeball_list_matters or smokeball_get_matter. There is no direct comparison to sibling tools or exclusion criteria, so an agent must infer usage from the name and the 'read' effect constant.

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