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

Annotations already mark it read-only, idempotent, and non-destructive; the description adds app-only visibility and that the response is limited to the diagram sequence number and whether it changed. It does not discuss polling cadence or auth, but the key behavioral context is disclosed.

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?

A single sentence front-loads the app-only audience, then states the behavior and return scope with no filler. Dense but readable, and every clause earns its place.

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 an app-only, read-only polling tool, the description covers audience, hidden-from-model behavior, and return shape, while annotations cover safety and the schema covers most parameters. Missing polling cadence is a minor gap.

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%, with diagramId, sinceSeq, and epoch already documented in the schema. The description adds no parameter-level detail beyond implying the sequence-number return, so baseline 3 is appropriate for a near-high coverage schema.

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 the specific audience and operation: refreshing the picture and live cursors in the in-chat viewer. It distinguishes app-only usage clearly, though the polling verb is implied rather than explicit.

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 limits use to the in-chat viewer (MCP App) and notes that clients supporting app-only tools hide it from the model, which tells an agent when not to call it. It does not name a model-facing alternative, but the exclusion is clear.

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