smokeball_get_matter

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false — so the safety profile is well covered. The description adds a couple of behavioral details beyond that: it asserts routing is restricted to the exact governed connector authority, and it documents that `effect` must be 'read' and that Spring verifies it. These are legitimate additions, since verification behavior is not visible in annotations. However, it doesn't disclose what the operation returns, whether it can fail, or what happens on invalid arguments. With annotations doing the heavy lifting, a 3 seems balanced — the description adds some context but not rich behavioral depth.

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 reasonably compact and front-loads the identity and routing constraints before the parameter list. The parameter bullet list is scannable and earns its place by naming each field. However, there's mild redundancy: 'Required and must be read' in the effect bullet repeats the schema's const='read' constraint. Overall, it avoids bloat and is well-structured, though not maximally tight.

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?

Given low schema coverage, no usage guidance, an active output schema (has_output_schema=true), and the fact that this is a get operation from a foreign system, the description is missing too much. It never explains what a matter is in Smokeball terms, how to target which matter to get, what the return payload contains beyond what the output schema provides, or how this differs from smokeball_get_matter_items / smokeball_get_matter_type. For a tool that an agent needs to invoke correctly, the absence of matter-selection semantics is a real completeness gap.

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%, so the description must compensate by explaining the parameters. It does list all seven parameters with one-line glosses, but the glosses are largely generic identity/tracing fields (project_id, project_ref, connector_account_ref, idempotency_key, approval_ref) that don't explain how to use them or which are needed for a get operation. The most important parameter, `arguments`, is described only as 'JSON string of arguments' — the actual matter-identification payload is left completely unspecified, which is critical for a get tool. The `effect` parameter's const='read' in the schema is reinforced by the description, but the agent still doesn't learn what to put in `arguments` to fetch a specific matter. With 0% schema coverage and 7 parameters, this is a significant gap.

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 the operation and says it routes through a governed connector authority, but never states what `get_matter` actually does — no verb like 'retrieve' or 'fetch' and no object description beyond the name. The name implies retrieving a matter from Smokeball, but the description itself is mostly boilerplate about routing and governance. A purpose-clarity score of 3 is appropriate: it's not a tautology or misleading, but it leaves the actual 'get' semantics implicit.

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 vs. alternatives. The sibling list includes smokeball_list_matters, smokeball_get_matter_items, smokeball_get_matter_type, smokeball_integrated_search, and smokeball_search, but nothing in the description mentions them or explains when one should be chosen over another. The only context given is 'routes through the exact project/account governed connector authority,' which is a routing constraint rather than a usage condition. No when-to-use or when-not-to-use guidance is provided.

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