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

Annotations already declare readOnlyHint=false and openWorldHint=true, but the description adds critical behavioral context beyond that: it emphasizes the privacy of the editToken ('never show it with the shared link'), which is not present in annotations. This extra security note provides valuable operational guidance. It stops short of describing rate limits or failure modes.

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 two sentences with no filler. The purpose and primary outputs are front-loaded, and the security warning is stated concisely. Every phrase adds information without redundancy.

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?

The description covers the essential return fields (URL, revision, editToken) and the critical privacy constraint, which is especially important given there is no output schema. It also implicitly directs the user to get_drawing_format for schema details. Minor gaps include missing error-handling or idempotency notes, but for a creation tool with a rich schema, this is adequate.

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 description coverage is 100%, so the schema already documents every parameter thoroughly. The description's mention of 'native canvas JSON' slightly reinforces the document parameter's nature, but this is already captured in the schema (e.g., 'Native editor document'). No meaningful additional parameter semantics are added 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 states a specific verb ('Publish') and resource ('native canvas JSON'), and clearly specifies the key returns: public URL, revision, and private editToken. This clearly distinguishes it from read siblings like get_drawing and mutation siblings like update_shape, making its purpose unambiguous.

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 description implies its usage for creating a newly published diagram and warns to retain the editToken for later edits, but it does not explicitly state when to prefer this tool over alternatives like set_drawing or update_shape. No direct 'when not to use' guidance is provided.

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