ghl_project_delete_task

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds genuinely non-obvious context: the exact response payload `{ success, id }`, that a repeat delete yields not-found rather than an error, the required OAuth scope `projects/tasks.write`, and the admission that cascade behavior is undocumented. Minor tension: the not-found-on-repeat behavior is worth flagging against idempotentHint=true, though the end state is unchanged.

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?

Roughly half the text is an API-wide preamble about hierarchy, batch-get RBAC filtering, lexorank `position`, and recurring task fields — none of which affects how this delete is called. The operational content (response shape, repeat-delete behavior, endpoint, scope) is buried after that preamble instead of front-loaded.

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 mutation with no output schema, the description supplies everything needed to invoke it correctly: method+path, version header, auth scope, return shape, and the honest caveat that cascade effects are undocumented. The only gap is that subtask deletion's effect on children is not stated, which it partly acknowledges.

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 the schema already explains the locationId channel nuance (APP query param vs. ignored for OAuth/PIT). The description adds nothing about either parameter, 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?

States a specific verb and resource ('Deletes a task or subtask by id') and names the exact id-keyed endpoint plus version header. An agent can distinguish this from sibling deletes such as ghl_project_delete_list or ghl_project_delete_space without opening a schema.

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?

It gives a useful destructive-usage warning ('treat every delete as destructive') and a repeat-call rule (second delete returns not found), but there is no explicit when-to-use vs. alternatives guidance — e.g., no routing to ghl_project_update_task or ghl_project_remove_list_task for the non-destructive cases. Usage is implied, not stated.

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