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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Read-only and deterministic' largely restates structured data. However, the description adds genuinely new behavioral information not present in annotations: the return comes as both a structured object and a short text version, which matters because there is no output schema. That added return-shape context justifies a 4.

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?

Three short sentences, front-loaded with what is returned and the list of content categories, with behavioral notes last. Nothing is padded. Minor deduction because 'Read-only and deterministic' duplicates information already carried by the annotations and could have been spent on when-to-use guidance.

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-parameter read-only tool with no output schema, the description covers both content scope and return format, which is most of what an agent needs. The remaining gap is sibling differentiation: with ten other memory_* tools available, an agent still lacks a stated rule for choosing this one over memory_get or memory_summarize.

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 there is nothing to disambiguate and the baseline of 4 applies. The description correctly implies the call is argument-free by describing it purely in terms of what it returns.

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 gives a specific verb and resource ('Returns a compact summary of what the user has saved about themselves') and enumerates the contents: lasting preferences, key facts, working style, active projects and open to-dos. That is far more concrete than the title alone. It does not distinguish itself from siblings such as memory_get, memory_summarize or memory_whats_up, so it stops short of a 5.

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 only implied: an agent can infer this is the tool for a quick profile overview because the description says 'compact summary'. There is no explicit statement of when to prefer it over memory_get, memory_summarize or memory_whats_up, and no exclusions. Adequate but leaves routing to inference in a crowded namespace.

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