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

With no annotations provided, the description carries the full burden. It discloses persistence duration (30 days from last write), size limit (64KB), and cross-session availability. It implies overwrite-on-write by saying 'from the last write', which is valuable behavioral context beyond the schema.

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 with zero wasted words. The usage trigger is front-loaded, followed by persistence and size constraints, then the retrieval pointer. Every sentence 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 two-parameter, simple write tool with no output schema and no annotations, the description covers all that an agent needs: when to use, what to provide, how long data lives, and how to get it back. Nothing essential 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 the baseline is 3. The description repeats the size limit already in the schema and adds the phrase 'small piece of text', but doesn't meaningfully enrich the parameter meaning beyond what the schema already provides. No extra semantics for key or value.

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 the verb 'save' and the resource 'a small piece of text on this server' and explicitly names the retrieval counterpart fetch_stash. This distinguishes it clearly from siblings like attest and get_conditions, making the tool's role unambiguous.

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 starts with 'Use this when you want to save...' and gives concrete persistence context (30 days, 64KB). It names fetch_stash as the way to retrieve, which is the key pairing. It doesn't explicitly list exclusions, but for a simple storage tool the guidance is sufficient.

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