Link Task to Context

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

With no annotations, the description carries the full burden and does well: it discloses that this is a mutation that appends to the END of the body (POST /blocks/append), that it is idempotent with existing block ids reported on a no-op, and that task_id must be a RootTask. It stops short of permission requirements, whether the target object's modified timestamp or notifications are affected, and what an error looks like when task_id is not a Task.

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?

Four short sentences, purpose front-loaded, then model, then mechanism/idempotency, then type constraint. The 'derived, not a property' aside is slightly academic but earns its place by explaining why the tool exists rather than setting a field. No filler.

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 and no annotations, the description covers purpose, mechanism, idempotency, and a partial return-value hint ('existing block id(s) are reported'). Gaps remain around auth/permissions and the full success response, but nothing an agent needs to invoke it correctly is missing.

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 coverage is 100%, so baseline is 3, but the description adds meaning not in the schema: task_id must specifically be a Task/RootTask (a type constraint the schema omits), and object_id can be any embeddable object such as a person, project, or meeting. That materially reduces wrong-type calls.

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 ('Add a task to another object's Context') and then defines the mechanism precisely: appending an EntityBlock embedding the task to the end of the target's body. The 'Context is derived, not a property' framing separates it conceptually from a plain property update and from unlink_from_context, even though append_to_object is never named.

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 implied by the derived-Context model, and the idempotency note tells the agent it is safe to call repeatedly. However, there is no explicit 'use this instead of append_to_object when...' routing, no prerequisite/permission note, and no pointer to unlink_from_context as the inverse.

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