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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered; the description adds ordering ('newest first') and a full inventory of returned fields, which the agent could not infer otherwise. It stays silent on pagination behavior beyond what the cursor param implies, and on rate limits.

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?

Two tight sentences: the primary behavior and its payload first, the alternative mode second. No filler, no restatement of the title, and the mode distinction is front-loaded where the agent will read it.

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, describing the returned fields and their order is exactly the right compensation, and the compare branch is at least characterized. The compare result itself ('what changed') is left vague, and pagination semantics for cursor/limit are left entirely to the schema.

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%, and the description adds genuinely new semantics: compare's from/to accept 'revision numbers or dates', which the schema only types as integer-or-string without explaining. 'to' defaulting to latest is repeated from the schema, and limit/cursor get no prose, but the schema covers them adequately.

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 ('Lists a diagram's versions') and enumerates the returned fields (time, by, client, message, chain hash, change counts), so the agent knows exactly what this produces. It also separates the tool's two modes (list vs. compare). It never names a sibling such as diagram_get or diagram_render, so sibling differentiation is left 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?

The final clause routes the agent between the tool's two modes: use the base call for a version list, use compare 'instead' to learn what changed between two versions. That is an explicit alternative with a selecting condition. There is no guidance about when to prefer this over siblings like diagram_get or diagram_find.

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