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

The annotations already declare this as a safe, read-only, idempotent, closed-world operation. The description adds useful behavioral details beyond the annotations: the default outline shape, the scene JSON and Mermaid return forms, and the NOT_FOUND behavior for another workspace's diagram.

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?

The description is front-loaded with the core action and then packs the important view and revision semantics into a compact paragraph. It is dense and could be easier to scan as a list, but every sentence carries useful information and there is no 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?

There is no output schema, but the description adequately describes the default return structure and the alternate view outputs. It also covers the key error case, though pagination via cursor is only described by the schema and not by the description.

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 71%, so the schema documents some parameters already. The description meaningfully supplements this by explaining the semantic difference between 'revision', 'asOf', 'knownRevision', and 'elements', though it does not explain 'cursor' pagination behavior beyond what the schema provides.

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 description opens with a specific verb+resource ('Reads a diagram') and then details what the default read returns, making the scope clear. It also distinguishes the mermaid view from diagram_edit by saying the Mermaid output is meant to be edited and sent back, so the agent can tell it apart from sibling mutation 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?

It explicitly explains the view modes ('outline', 'dsp', 'mermaid') and when each is useful. It also names the revision-selection parameters and their distinct purposes: 'revision or asOf reads an earlier version', 'knownRevision' shows only changes since a revision, and 'elements' limits output to those elements and neighbors.

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