bulk_update_tasks

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

With zero annotations, the description carries the full disclosure burden and delivers: partial-update semantics ('Only the fields you pass are written'), a per-project write-access requirement, and an all-or-nothing failure mode ('the whole request is refused and nothing changes'). This goes well beyond generic 'update' language and prevents an agent from assuming partial success or that omitted fields are cleared.

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?

Three short paragraphs with the purpose front-loaded in the first sentence. The only mild redundancy is the middle paragraph's three sentences all circling the single point 'this is a partial update on both versions'; informative, but it could be tightened into fewer sentences.

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 3-parameter mutation with no annotations and no output schema, the description covers the decision-critical facts: fields affected, partial-update behavior, permissions, and atomic failure. The notable omissions are the response shape (no output schema exists to carry this) and any maximum batch size for task_ids.

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 0%, so the description must compensate — and it does by clarifying the key gotcha: only passed fields are written, meaning omitted optional parameters are untouched despite their null defaults. task_ids is also implicitly scoped across multiple projects via the 'every project involved' permission note. It stops short of explaining explicit-null behavior (does done:null clear the field?) or any priority value range.

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 first line names a specific verb ('Set'), the exact writable fields (`done`, `priority`), and the scope ('many tasks in one request'). This clearly differentiates it from siblings like update_task (single task) and bulk_create_tasks (creation), so an agent can route correctly without opening any schemas.

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 description states the tool works 'on either API version' and contrasts its behavior with single-task update, which is a replace on v1 — clear context for when the bulk endpoint is appropriate. However, it never explicitly names sibling alternatives or states when-not-to-use it, so exclusions remain implied rather than stated.

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