Visualizer

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 useful behavior: 'start' spins up a server and opens a web UI, 'stop' tears it down, 'get_graph' returns JSON, and 'open' returns a URL. But it says nothing about port binding, whether start is idempotent, what happens to an existing server, or whether stop destroys state — all material for a stateful server-lifecycle tool.

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?

Front-loaded with the purpose followed by a scannable action list, then capability bullets. It is slightly longer than needed — the 'visualizer shows' bullets are nice-to-have context rather than invocation guidance — but no sentence is pure filler.

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 six-operation stateful tool with no annotations and no output schema, the description should say more about return values for get_graph/status/open and about server lifecycle edge cases. It covers the happy path adequately but leaves an agent guessing about failure modes and per-action preconditions.

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 coverage is 75%, so the baseline is 3, but the description earns an upgrade by explaining what each enum value actually does ('focus: Focus on a specific node', 'set_context: Update current file/task context') and tying node_id/file/task to their actions. The only gap is that no value formats or required-per-action combinations are stated.

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 opening line names a specific verb-and-resource combination ('interactive graph visualization of code dependencies') and the action list spells out each operation precisely. An agent can tell this is a server-lifecycle plus graph-query tool. It does not, however, differentiate itself from siblings like mcp_m7_impact or mcp_m7_knowledge_graph, which cover overlapping visualization/impact territory.

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 closing line gives a minimal workflow hint ('Use start to launch, then open the URL in browser'), but there is no guidance on when to pick this over mcp_m7_impact for impact analysis or mcp_m7_knowledge_graph for graph data, nor any stated prerequisites or exclusions. Usage is implied by the action names rather than explained.

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