save_memory

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

With no annotations, the description carries the full burden and does real work: it discloses that metadata parse failure stores an empty dict and returns a warning, and that a supplied collection is created automatically if missing. Less positive traits are undisclosed, notably whether saving duplicate text overwrites or appends, and no auth/permission context is given.

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 core purpose leads, followed by the two non-obvious parameter behaviors, with no filler sentences. The parenthetical JSON example is slightly heavy but earns its place by resolving the string-vs-object ambiguity.

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?

An output schema exists, so return values need not be explained, and the description still notes a warning is returned alongside the result. For a 3-parameter mutation tool with no annotations, this is nearly complete; the main omission is duplicate/overwrite behavior and permission requirements.

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 0%, so the description must compensate and largely does: it explains that metadata accepts either a JSON string or a JSON object, documents the failure fallback, and explains collection semantics including the default. Only 'text', the sole required parameter, is left unelaborated, which is self-evident.

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?

States a specific verb and resource with scope: 'Save a new document or scenario outcome into the vector DB.' An agent knows this is a write-to-vector-store operation, but the description never distinguishes it from the near-identical sibling save_memories (plural) or from update_memory, which is the real risk here.

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 word 'new' implies creation as opposed to update_memory, but this is inference rather than guidance. There is no explicit when-to-use, when-not-to-use, or named alternative despite three closely related siblings, so an agent has no stated basis for choosing between save_memory, save_memories, and update_memory.

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