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

The annotation already declares readOnlyHint=false, so the description's explicit 'WRITES' warning adds context by detailing that stored state changes and that blind repetition is unsafe. The idempotency condition adds nuance beyond the annotation, which is valuable.

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?

The description is only two sentences and front-loads the core purpose ('Maintainer only: compute signed Merkle checkpoints now.') followed by the idempotency caveat and a clear write warning. Every sentence earns its place without redundancy.

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 write operation with one parameter and no output schema, the description covers the essential behavioral aspects (write, idempotency) but leaves the 'secret' parameter entirely unexplained. It also doesn't mention what the response might look like, which is a gap for a maintenance tool that likely returns a checkpoint or status.

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?

The schema has a single 'secret' parameter with no description, and the tool description provides zero explanation of what 'secret' is for or how it should be formatted. With 0% schema description coverage, the description was expected to compensate, but it fails to do so.

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 action ('compute signed Merkle checkpoints now') and identifies the resource (a log's checkpoint). It also notes 'Maintainer only', which clarifies the intended audience. This distinguishes it from read-only siblings like 'checkpoints' and 'checkpoint_consistency'.

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 clearly indicates a restricted audience ('Maintainer only') and gives a specific condition for safe repetition (idempotency when the tree size is already checkpointed). However, it doesn't explicitly mention alternatives or when not to use this tool beyond the maintainer restriction, so it stops short of full routing guidance.

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