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

Annotations only declare readOnlyHint=false, so the description carries the real disclosure load and does it well: it states this WRITES stored state, that it is not safe to repeat blindly, and that it is idempotent only when the tree size is already checkpointed. That conditional idempotency nuance is exactly the context an agent needs before re-invoking a mutation.

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 tight sentences: the maintainer restriction and action are front-loaded, followed by the write/idempotency warning. No filler, and the most safety-critical clause is not buried.

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 one-parameter mutation tool with readOnlyHint=false and no output schema, the description covers access, write semantics, and idempotency well. The only real gap is the undocumented secret parameter, which the schema also leaves blank.

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 single 'secret' parameter has 0% schema description coverage, so the description must compensate and largely does not. 'Maintainer only' hints that the secret is a maintainer credential, but the description never explicitly identifies or explains the parameter, leaving its format and role to inference.

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 ('compute signed Merkle checkpoints now') with a clear scope, which separates it from the read-only checkpoint_consistency and checkpoints siblings. It stops short of naming an alternative explicitly, so it is clear but not fully sibling-differentiating.

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?

'Maintainer only' gives a clear access precondition for when this tool is callable, and 'now' signals a manual trigger. It offers no explicit exclusions or named alternatives (e.g. checkpoint_consistency) for when not to use it.

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