memory_related

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

The readOnlyHint=true annotation already establishes the safety profile, so the description's burden is lower, but it adds almost nothing beyond that. It does not explain what the two modes ("recent" vs "timeline") do behaviorally, how as_of interacts with mode, whether results are paginated via limit, or what happens when the entity is unknown or ambiguous between a name and an alias.

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?

It is a single short sentence with no filler, which is efficient, but it is under-specified rather than concise — the length comes at the cost of not front-loading an action or the mode/paging behavior an agent needs.

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 four-parameter tool with a mode enum, an as_of date filter, a limit, and no output schema, the description leaves too much unsaid: neither the mode behaviors nor the return shape are described. An agent could call it, but could easily misuse mode/as_of or misjudge the results.

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 only 25% (only as_of is documented in-schema), so the description should compensate, and it only partly does: the parenthetical "(name or alias)" clarifies that the entity parameter accepts aliases, which is genuine added meaning. The mode enum, limit, and as_of semantics are left entirely unexplained in both places, leaving three of four parameters opaque.

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?

"Notes about one entity (name or alias) and the entities mentioned with it" conveys the resource — co-mention notes for an entity — but it is a bare noun phrase with no verb and the word "Notes" is ambiguous (stored notes? relationship hints?). It does not name or contrast with siblings memory_get, memory_list, or memory_search, so the agent must infer that this is a related-entity lookup.

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?

There is no when-to-use guidance at all: nothing says whether to call this instead of memory_get for a single entity, or instead of memory_search when exploring associations. No prerequisites, no exclusions, no alternative named.

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