ghl_project_update_recurring_task

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

Annotations already declare readOnly=false, idempotent=true, destructive=false, and openWorld=true. The description adds useful context beyond that: the PUT endpoint, v3 version header, OAuth scope projects/tasks.recurring.write, and the distinction between recurring-task fields and task-create fields. It does not explicitly state partial-vs-full update behavior or whether generated task instances are affected, but with annotations present this is a solid disclosure.

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 actual tool-specific purpose is buried after a long API-wide preamble covering hierarchy, batch-get RBAC behavior, lexorank `position`, task search `updatedAt`, and delete cascades. Most of that context is irrelevant to updating one recurring task, so the structure is not front-loaded and the description is unnecessarily bloated.

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?

Given the rich input schema, annotations, and no output schema, the description supplies enough operational context: endpoint, HTTP method, version header, OAuth scope, and recurring-task field semantics. It could be stronger by clarifying update replacement/partial semantics, but it is broadly complete for calling the tool.

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 baseline would be 3. The description adds real parameter meaning by noting that recurring tasks use `owners`/`contactIds` and `rruleOptions.intervalType`, while regular task creation uses `assignees`/`contactId`; this directly helps an agent avoid using the wrong field names.

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 gives a specific verb and resource: 'Updates schedule or template fields on an existing recurring task definition.' This clearly identifies the operation as an update to a recurring task, though it does not explicitly name sibling alternatives such as create/delete recurring task or location recurring-task update.

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 endpoint and OAuth scope imply when the tool is applicable, and the phrase 'existing recurring task definition' signals it is not for creation. However, there is no explicit guidance on when to use this versus ghl_project_create_recurring_task, ghl_project_update_task, or the location-level recurring-task update.

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