memory_bootstrap

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

With no annotations provided, the description carries the full behavioral burden, and it delivers: it discloses the aggregation behavior (rules + preferences + recent + optional query matches), the ordering ('by importance'), and the optionality of semantic matching. It does not confirm side-effect-freeness or describe edge cases like an empty memory store, but 'load' clearly implies a non-mutating read, and the result composition is well conveyed.

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 waste: the first front-loads verb, resource, purpose, and result composition; the second is a terse call-to-action. Every clause earns its place, and no information is buried.

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 moderately complex aggregation tool with no output schema and no annotations, the description covers the essentials an agent needs to invoke it correctly: what it returns (result categories and ordering), when to call it (session start), and parameter control (schema-provided defaults). Minor gaps remain—return format is unspecified and edge behavior (empty store, overlap between recent and matches) is unaddressed—but the description compensates well for the missing structured metadata.

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 schema already documents all four parameters with defaults inline. The description adds only marginal mapping value by tying the limit parameters to the result categories (rules/preferences, recent, query matches), which is helpful but not substantive new semantics. Baseline 3 is appropriate.

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 opens with a specific verb and resource ('Load relevant memories') and a clear purpose ('to bootstrap a new session'), then enumerates exactly what comes back: top rules/preferences by importance, recent memories, and optional query matches. This composition distinguishes it from sibling memory_search (targeted retrieval) and the mutation/state tools (add/clear/forget), so an agent can tell them apart without opening schemas.

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?

'Call at session start' is explicit, crisp usage guidance that anchors when this tool applies. However, it does not mention exclusions or route to alternatives (e.g., 'for targeted lookups mid-session, use memory_search instead'), stopping one step short of the full when/when-not/alternatives standard.

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