schema_change_report

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

With no annotations, the description carries the full burden. It does disclose the return shape (structured JSON of nodes + edges with change-activity counts, non-visual) and the behavior when focus is omitted (overview of most consequential items), which is genuinely useful. It says nothing about pagination/limit effects, whether counts are scoped by `since`, or any auth/latency characteristics for a graph-producing read.

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 core identity and the 'no UI' contrast are front-loaded, and each view sentence earns its place with a concrete example. It is dense but readable; the repeated 'focus_object = ...' phrasing is slightly redundant against the schema and could be tightened.

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?

No annotations and no output schema, so the description must cover behavior and returns — it partially does by describing the node/edge payload. Gaps: the `object_name` vs `focus_object` naming conflict, no explanation of `limit` or how `since` interacts with the reported change counts, and no routing to the many sibling tools that overlap (get_permission_context, expand_schema_node).

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 60%, so the description must compensate, and it does well for `view` (all three enum values explained with example focus objects). However, it refers to the focus parameter as `focus_object` while the actual schema property is `object_name` — a naming mismatch that can lead an agent to pass the wrong key. `limit` (min 5, max 100) is undocumented anywhere.

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 specific resource (the schema/permission/role graph as nodes + edges with change-activity counts) and explicitly distinguishes itself from the sibling visualizer ('Same data as visualize_schema_graph, without rendering it'). The three view modes are enumerated with concrete examples, so an agent knows exactly what it gets. It falls short of 5 only because there is no crisp verb framing of the operation itself.

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?

It routes the agent per view with concrete guidance ('use this to compare what different roles can actually do') and states the omit-focus_object behavior for overview queries. The 'no UI' / 'same data as visualize_schema_graph, without rendering it' line implies when to pick this over the visualizer. There is no explicit statement of when NOT to use it or what other siblings (e.g. get_permission_context, expand_schema_node) cover instead.

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