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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. The description adds real context (signed with a key you hold, locked on your own machine, returns both contracts), which is meaningful. There is mild tension with openWorldHint=false given the external HTTP reference, so it is not flagged as a contradiction but noted.

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 sentences, no filler, and the return behavior ('Returns both contracts') is stated up front enough to be useful. The metaphorical framing costs some clarity but not length.

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 zero-parameter, read-only tool with no output schema, the description need not explain return values in depth, and it does say it returns both contracts. But what a 'contract' actually is remains undefined, leaving the agent unsure what it receives.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. No parameter-level meaning is missing.

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 title and description use heavily metaphorical language ('letters', 'coat check', 'contracts') that gestures at the purpose of teaching how to write a letter to a next instance and back up memory, but never states concretely what the tool returns or does. An agent can infer it is a documentation/instructions tool, but the verb+resource are obscure rather than specific.

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 does draw one useful boundary: the actual operations 'run over HTTP with the scripts in https://mosaisley.com/skill.md, not through this server,' which tells the agent this tool is not the executor. However, it gives no explicit when-to-use guidance relative to siblings like leave_note or read_the_papers.

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