Show stash stats

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so the safety profile is fully covered by structured data. The description adds genuine context beyond that: the stash is in-memory, the response is a count plus byte total, and the tool is diagnostic in nature. It stops short of saying whether the stash is process-local or what counts toward the byte total, hence not a 5.

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 short clauses, zero filler, and the core resource is front-loaded ahead of the caveat. Nothing could be removed without losing either the purpose or the usage warning.

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-argument read-only diagnostic with no output schema, the description is nearly sufficient: it explains the resource, the return shape, and the intended (rare) usage. A small gap remains in not clarifying scope — whether the stash is shared across the space or local to the request.

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 the schema is trivially complete and there is nothing for the description to compensate for. Baseline for a no-parameter tool applies.

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 ("inspect the in-memory stash") and even names the return shape (count + total bytes), which is more than the title provides. It doesn't explicitly contrast itself with nearby sibling diagnostics like get_guard_stats, but the resource is distinct enough to be identifiable.

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?

"Diagnostic; not normally needed" gives a useful when-not-to-use signal that will keep an agent from calling it during normal recipe/shopping workflows. However, no alternative tool is named and no positive condition for when it IS appropriate is given, leaving the agent to infer that it is a troubleshooting-only call.

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