save_memory

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

With no annotations provided, the description carries the full behavioral burden, and it does disclose the critical gating behavior: the session must originate from an exact trigger phrase and user_confirmed must be an explicit final confirmation. It does not describe side effects (e.g., what becomes visible or public, whether the write is reversible), so it stops short of full transparency.

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 tight sentences with the most critical constraint ('Never call directly') front-loaded immediately after the identity sentence. There is no filler, and each sentence adds a distinct precondition.

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 13-parameter mutation with no annotations, no output schema, and 0% schema description coverage, the description covers the authorization/gating story well but leaves the semantics of most inputs undocumented. An agent knows when it may call the tool but not what most of its arguments should contain.

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% across 13 parameters, so the description must compensate and largely does not. Only 'context' is hinted at ('required context fields') and user_confirmed is confirmed as a hard requirement; parameters like visibility, wording_mode, source_type, tags, owner_token, and what_to_save are never explained, leaving the agent to infer their meaning from names alone.

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 frames the tool as the 'FINAL save step after start_memory_save_interview', which states both the operation (persisting a memory) and its position in the workflow, and explicitly differentiates it from the sibling that begins the flow. The core verb+resource ('save memory') is carried mostly by the name rather than restated, but the sequencing context is unambiguous.

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?

It gives explicit when/when-not guidance: 'Never call directly', only after start_memory_save_interview, only with a valid session, only with the exact trigger phrase, and only with explicit final user confirmation. An agent has no inference left to make about routing.

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