memory

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

The annotations already flag the tool as non-read-only and destructive, and the description adds useful behavioral detail beyond that: download can write to outPath or return base64, upload moves a local file into memories, and delete removes a memory. It does not contradict the 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?

The description is intentionally compact and front-loads the resource type before the action list. The dot-separated action markup packs a great deal of information into one sentence, though the 'then attach' wording inside upload is slightly ambiguous and the dense punctuation requires careful parsing.

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?

With seven actions, ten parameters, no output schema, and no return-value descriptions, the definition is not complete enough for safe invocation. The agent does not learn which parameters are required per action, what enum values mean in context, how pagination works, or what each action returns.

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 20%, so the description must compensate for many undocumented parameters, but it only clarifies outPath, memoryId, and personId indirectly per action. Parameters like count, start, title, description, filePath, and personName are left unexplained, leaving the agent to guess which action each belongs to and what values are expected.

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 states the resource ('Memories (photos, documents)') and enumerates seven concrete actions with verbs and objects: list_person, list_mine, get, download, upload, attach, and delete. This makes the tool's purpose unambiguous and differentiates it from sibling tools like note or person, even without detailed prose.

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 context 'Memories (photos, documents)' and action list imply when the tool is relevant, but the description never explicitly says when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. The usage guidance is present only by implication, not by direct instruction.

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