session_diagram

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

No annotations are provided, so the description bears the full disclosure burden. It does add genuinely useful behavioral context: the tool auto-scans project files to build the dependency graph, and the output must be 'passed to a Mermaid renderer to visualize' (i.e., the tool does not render itself). However, it does not disclose whether `regenerate` is destructive, whether sessions cache diagrams, or any side effects from the auto-scan — gaps that matter for a mutation-ish tool with zero annotation coverage.

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?

Three tight sentences, each earning its place: the main purpose is front-loaded, the auto-scan behavior follows, and the renderer hand-off closes. No filler or redundancy. It loses one point only because the session-based behavior implied by `session_id` is never mentioned, leaving a small completeness gap in an otherwise efficient structure.

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 tool with 3 params, no output schema, and no annotations, the description is serviceable but incomplete. It explains the auto-scan and Mermaid output but never mentions the session dimension that `session_id` depends on, gives no return-format detail (Mermaid string length, cache behavior), and leaves the required `project_root`'s role only loosely implied. What is needed to call the tool correctly is mostly covered; the session semantics and output expectations are not.

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 67%: `regenerate` and `session_id` are already well-documented in the schema, leaving the required `project_root` undocumented. The description's 'Auto-scans the project files' gives `project_root` useful context (it is the root scanned to build the graph), which partially compensates. But the description never ties the `session_id`/session-cache concept to the schema, so it adds only marginal value over what the schema already states.

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?

Clear verb+resource pairing: 'Show or regenerate the architecture diagram' in 'Mermaid format', with the auto-scan behavior explicitly stated. All sibling tools are session lifecycle operations (init, checkpoint, load, update, status, log) or claims, so the diagram focus is self-evidently distinct even though no sibling is named — unlike a high-5 there's no explicit 'use X instead' comparison, so it stops at 4.

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?

No explicit when-to-use or when-not-to-use guidance, and no alternatives are named. Usage must be inferred from the purpose statement ('Show or regenerate the architecture diagram'). The sibling tools are all session operations so confusion is unlikely, but the description does not actively route the agent — this is implied usage at best, meriting a 3.

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