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

Annotations are all false (not read-only, not idempotent, not destructive), and the description does not contradict them. It adds useful behavioral context: the DAY_MARKER rule for separating days and the fact that this is the sole write mechanism. It doesn't disclose retry semantics, but those are implied by idempotentHint=false and the client_id param in the schema. This is a reasonable amount of added context beyond the annotations.

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?

Two sentences, zero filler. The purpose is front-loaded, the key domain rule (DAY_MARKER) is included, and the reference to learn is concise. Every clause earns its place.

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 tool with 8 params, a nested payload object, and an enum, the description is concise but sufficient because it defers to learn('block_types') for the complex payload details. It doesn't describe return values, but there's no output schema, so that's not required. It covers the core action and provides a clear path to the necessary knowledge.

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% with each parameter described, so the schema carries the heavy lifting. The description adds value by pointing to learn('block_types') for payload shapes, which directly addresses the most complex parameter (payload). It also implicitly reinforces the client_id deduplication purpose by mentioning 'only way to write,' though it doesn't restate the schema details.

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 description states a specific verb ('Add'), resource ('block'), and scope ('to a trip's timeline'). It also declares 'This is the only way to write to a timeline,' which distinguishes it from read-only siblings like get_timeline and update_block. This makes the tool's purpose unmistakable.

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 explicitly establishes when to use this tool: 'This is the only way to write to a timeline.' It also directs the agent to learn('block_types') for layout specifics, which is a clear pointer for payload construction. It doesn't mention alternatives for updating existing blocks, but given that it's the only write path, the usage context is clear.

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