ghl_project_get_recurring_task

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context (auth scope, version header, endpoint), but most of its behavioral notes — batch-get RBAC omission, lexorank `position`, delete cascade — pertain to other tools and leave this read's not-found/access-denied behavior unspecified.

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 purpose appears only after a large block of shared project-management boilerplate about hierarchy, batch-get RBAC, lexorank ordering, search sync, and delete cascades — almost none of which affects calling this single-item GET. The definition is back-loaded and wastes the agent's attention before the operative sentence.

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 two-parameter read with annotations and no output schema, the endpoint, id requirement, and auth scope are enough to invoke it. The one genuinely relevant detail — that recurring tasks carry `owners`/`contactIds` and `rruleOptions.intervalType` rather than `assignees`/`contactId` — is present but buried, and response shape is otherwise unaddressed.

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%, and both `id` and `locationId` already document their channel-dependent behavior fully, including "ignored for OAuth/PIT." The description adds nothing beyond the schema here, so the baseline 3 applies.

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 second section states a specific verb and resource: "Get Recurring Task By Id — Fetches one recurring task definition by id," plus the exact endpoint. However, it never distinguishes this from sibling readers such as ghl_project_get_task, ghl_project_batch_tasks, or ghl_location_get_recurring_task_by_id, so the agent must infer which reader applies.

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, v3 version header, and required OAuth scope (projects/tasks.recurring.readonly) implicitly define the calling context, but there is no explicit "use this when… / use X instead" guidance and no statement about what happens when the id is inaccessible or unknown. Usage is inferable rather than stated.

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