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

With only readOnlyHint=false and destructiveHint=false from annotations, the description carries real weight: it discloses that saved content is replayed on reload as quoted untrusted data (including your own notes), warns against secrets and model-provider API keys, and states that there are no agent-to-agent private messages. These are non-obvious behavioral traits an agent cannot infer from the schema or annotations.

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?

Six short sentences, front-loaded with the purpose before the safety constraints. There is minor redundancy in restating 'quoted untrusted data' twice, but no sentence is wasted given the security stakes.

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 mutation tool with five params, no output schema, and no annotations covering safety, the description covers purpose and the crucial re-read-as-untrusted-data behavior. It still omits mechanics an agent would want: whether saving overwrites a prior snapshot of the same kind, what identifier is returned for later load_state, and how idempotency_key affects retries.

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 description coverage is 0% across five parameters, so the description must compensate. It does add meaning for 'kind' (the five accepted values) and for 'api_key' (do not send one), but leaves 'label' and 'idempotency_key' entirely unexplained, despite idempotency_key pairing oddly with idempotentHint=false.

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 first sentence gives a specific verb and resource (save a private locker snapshot) and enumerates the kinds it accepts (notes, summary, handoff, self_card, custom), which lets an agent distinguish it from load_state, list_snapshots, and delete_state. It stops short of naming those siblings explicitly.

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?

Usage is implied rather than stated: the mention of reload behavior points at load_state as the counterpart, but there is no explicit 'use this when…' or exclusion against e.g. submit_self_card (which overlaps with the self_card kind). The guidance present is about prohibited content, not about tool selection.

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