ghl_project_batch_tasks

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

Annotations already cover the safety profile, yet the description still adds genuinely useful behavior: inaccessible ids are silently omitted rather than erroring (prevents pointless retry loops), embedded `subtasks` are not returned, and the required OAuth scope (projects/tasks.readonly) plus v3 version header are stated. It does not describe the response envelope or pagination. Note the annotations mark readOnlyHint=false and idempotentHint=false for what is plainly a read-only batch fetch; the description is the accurate signal here, not the annotation.

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 two thirds of the text is a generic 'PROJECT MANAGEMENT API' preamble about hierarchy, lexorank `position`, recurring task field naming, and delete cascade behavior — none of which is actionable for a batch-get by id. The tool-specific content is buried after that preamble instead of front-loaded, so the agent must read past irrelevant material to find the two sentences that matter.

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 batch read with no output schema, the description covers the non-obvious essentials: silent RBAC omission, absent subtasks, scope, and version header. Missing is any hint about the returned task object shape or whether an empty result versus a partial result should be interpreted differently, but the core call decisions are supported.

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 both `ids` (1–100, examples) and `locationId` (required for APP channel, ignored for OAuth/PIT, not to be sent in path/body/headers) are already fully documented in the schema. The description adds no parameter-level detail beyond the RBAC consequence of passing ids, so 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 core sentence is specific: 'Fetches multiple tasks by id in one call,' giving verb + resource + batch semantics that distinguish it from the single-task sibling ghl_project_get_task. However, the definition never names that sibling or ghl_project_search_tasks, so the agent must infer the batch-vs-single distinction from the wording alone rather than being routed explicitly.

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?

Usage is only implied. The preamble notes that 'Task search supports updatedAt filtering/sorting for incremental sync,' which hints that ghl_project_search_tasks exists as an alternative for filtered retrieval, but the description never says when to prefer this batch-get over that search or over single-task get. There are no explicit when-not conditions.

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