update_web_packages

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

Annotations are minimal (readOnly=false, idempotent=false, destructive=false), so the description carries the burden and does so thoroughly. It discloses batch semantics, the silent-ignore behavior of non-writable fields, why the tool refuses them, the display_name/title timing caveat, and the required OAuth scope. None of these contradict the annotations.

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 ('Rename web packages. This is a BATCH operation.') and then layers necessary caveats in readable paragraphs. Every sentence adds value—auth scope, item shape, silent-ignore behavior, display_name lag, and the replace-content alternative—without repetitive 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?

Even though there is an output schema, the description fully covers what an agent needs to call this correctly: input shape, restrictive write model, failure mode (silent ignore), verification caveat, and auth requirement. It also handles the 'rename appears to do nothing' edge case explicitly, so an agent can verify success by reading title.

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?

The schema only defines an array of generic objects with additionalProperties=true, so it provides essentially no per-field meaning. The description compensates fully by specifying the exact item shape {id, title}, noting title is the only writable field, and naming the fields (type, state, base_path, display_name) that will be rejected.

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 precise verb+object pair: 'Rename web packages' and frames it as a batch operation. It also distinguishes itself from create/delete siblings by emphasizing that title is the only writable field, so an agent immediately knows this is a rename-only endpoint.

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 tells agents when this tool is appropriate (renaming, batch) and gives a clear alternative for a different need: 'To replace a package's content, create a new package and repoint the lesson.' It also warns that the tool refuses non-writable fields rather than silently accepting them, which helps an agent decide how to construct the call.

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