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

Annotations already flag destructive=true, but the description earns credit by explaining *why*: description is set wholesale and an empty/omitted value CLEARS it. That is the precise failure mode an agent must avoid, and it is stated plainly with a recovery procedure (read then pass both fields).

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 sentences, front-loaded with the scope and the destructive-replace warning before the procedure. It is dense with nested parentheticals, which slightly hurts scanability, but no sentence is 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?

For a destructive metadata mutation with an output schema and full schema coverage, this covers scope, destructive semantics, sibling routing, and the read-before-write procedure. Nothing an agent needs in order to call it safely is missing.

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 already 100%, yet the description still adds meaning the schema cannot: display_name is required, description is replaced wholesale rather than merged, and slug is not a parameter at all. That is genuine semantic value beyond the field-level docs.

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 (update a workflow) and narrows the scope to display_name and description only. It explicitly says what it does NOT do (workflow logic, slug) and names the siblings that handle the excluded work (create_workflow_version / patch_workflow), so an agent can distinguish it from patch_workflow without opening schemas.

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?

Gives explicit routing rules: use create_workflow_version or patch_workflow to change logic, and use get_workflow first when changing only one metadata field. It also names the one thing you cannot do (change the slug), which is exactly the kind of exclusion an agent needs.

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