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

Annotations declare idempotent and non-destructive hints; the description goes beyond by revealing that memory is scoped by user identifier, persists for authenticated users, or expires after 24 hours for anonymous sessions. It omits overwrite semantics but provides valuable behavioral context beyond 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?

Two sentences pack purpose, usage triggers, storage mechanism, retention policy, and related tools with zero wasted words. The structure front-loads the core function and then gives operational details.

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 simple two-parameter key-value store, the description covers purpose, when to use, storage scoping, persistence, and relationships to recall/forget. No output schema exists, but return format is not complex. All necessary context is present.

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 descriptions for key and value cover 100% of parameters, so the baseline is 3. The description adds illustrative examples of keys (e.g., 'subject_property', 'target_ticker') but does not fundamentally extend schema meaning. It provides marginal value above the schema.

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?

Description opens with the specific verb 'Save' and resource 'data the agent will need to reuse later,' clearly distinguishing from sibling recall/forget by stating it stores data. Examples of use cases further clarify scope. The description also explicitly pairs with recall and forget, cementing its unique role.

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?

The description provides explicit trigger conditions ('when you discover something worth carrying forward') and concrete examples (resolved ticker, target address). It mentions related tools (recall, forget) but does not explicitly state when not to use this tool, so it falls short of a 5.

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