update

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

No annotations are provided, so the description fully bears the burden of behavioral disclosure. It transparently explains that tags and shortcuts are strictly additive, metadata deep-merges last, and tags cannot be removed via the tags field—only through metadata or a delete/recreate workflow. The mention of v2 future plans adds additional context.

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?

The description is a single paragraph that efficiently front-loads the purpose and then details behavioral semantics. While every sentence is valuable, the structure could be improved (e.g., bullet points for additive vs. replace behavior). It is slightly dense but not overly verbose.

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?

The description assumes knowledge of the 'remember' tool's shape and does not specify return values or prerequisites (e.g., that the memory must exist). Given the absence of an output schema, the tool would benefit from describing what the response contains or confirming the update. It is adequate but has clear gaps.

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 100%, but the description adds significant value beyond the schema: it explains that 'every field is optional and unset fields are left untouched', describes the additive semantics for tags/shortcuts, and clarifies the deep-merge behavior of metadata. This extra context is crucial for correct invocation.

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 clearly states 'Update an existing memory' and explains that it accepts the same shape as 'remember' but with all fields optional. This directly conveys the verb (update) and resource (memory), effectively distinguishing it from sibling tools like 'remember' (create) and 'forget' (delete).

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 implicitly defines when to use the tool (to modify an existing memory) and notes the additive behavior for tags/shortcuts and how to work around tag removal. However, it does not explicitly state when not to use it (e.g., if full replacement is needed) or compare against alternatives like 'delete + recreate', leaving a slight gap in guidance.

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