Save a voice-derived note as a memory with title, transcript, optional summary, and tags, enabling later search and retrieval.
Save a new memory. title (<=200 chars) and transcript (<=100000 chars) are required; summary <=2000 chars; up to 20 tags of <=50 chars each.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| title | Yes | ||
| summary | No | ||
| transcript | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the write/non-destructive profile is covered. The description adds useful hard limits (character caps, 20-tag cap), but does not mention that repeated saves are non-idempotent and may create duplicates, nor what is returned.
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?
A very compact, front-loaded statement of purpose followed by the constraints; every clause carries information and nothing is filler. The constraint list is dense but readable.
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 4-parameter creation tool with 0% schema coverage and no output schema, the description documents all parameters, their required/optional status, and their limits. It omits duplicate-handling behavior and any indication of the returned identifier, which are minor 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 0%, so the description carries the burden and handles it well: it marks title and transcript as required and adds max-length constraints for title (200), transcript (100000), summary (2000), and tags (20 tags x 50 chars) that the schema does not express. Only the null-default nature of tags/summary is unstated.
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 ('Save a new memory') that clearly separates it from the read-oriented siblings (get_voice_memory, search_voice_memories, list_voice_tags). It is unambiguous what the tool does, though it never explicitly names a sibling or contrast case.
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?
Usage is only implied: the tool is the sole write operation among read siblings, so an agent can infer when to use it, but there is no explicit when/when-not guidance or mention of alternatives such as updating an existing memory instead of creating one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.