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

Annotations already cover read-only, idempotent, non-destructive and closed-world behaviour, so the description doesn't need to repeat them; it adds real value by describing the return shape (components with type/technology/description, connections with resolved endpoint names) and the deliberate exclusion of canvas geometry. Missing only error behaviour for unknown or deleted diagram ids.

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 action and the returned payload, then the geometry caveat, then the sibling pointers. Every clause earns its place; nothing repeated or padded.

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?

With no output schema, the description carries the return-shape burden and does so competently, plus it names the diagram taxonomy and id source. It would be complete at 5 with a note on what happens for a stale id or an unauthorized diagram.

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?

Only one parameter and schema coverage is 100%, so the schema already documents `diagramId` as a UUID. The description contributes only the hint to obtain ids from list_diagrams, which is a baseline-level addition rather than new format or constraint detail.

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?

States a specific verb and resource (read one architecture diagram), enumerates the diagram kinds covered, and describes exactly what is returned: a semantic graph of typed components and named connections, with canvas geometry omitted. That distinguishes it immediately from list_diagrams and from the broader context tools.

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?

Explicitly points to list_diagrams for id discovery and to the `diagrams` section of get_story_context for story-linked diagrams, which is clear routing guidance. It stops short of saying when not to use it, e.g. when a design or process document would be the better source.

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