subscribe_memory_event

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

With no annotations provided, the description carries the full burden, and it does well: it discloses that the subscription is a cursor rather than a callback, explains the architectural reason, and states that the tool is refused on stores without an event table. It could additionally state whether any state is stored, but the core non-obvious behavior is clearly disclosed.

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 dense but well organized: the core result is front-loaded, followed by the callback limitation, the companion poll tool, the Python alternative, the default semantics, and the failure mode. Every sentence earns its place and there is no redundant filler.

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 tool with one optional parameter, no output schema, and no annotations, this description is complete: it explains the return shape, how to consume it, what the default means, how this tool relates to poll_memory_events, and when it will be refused. An agent has enough context to call it and use the result correctly.

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 for the single parameter. It explains that the default '*' means every event type and applies 'on both calls', which adds real meaning beyond the schema's bare default. It does not enumerate valid event_type values, but no enums exist and the parameter is otherwise self-descriptive.

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 opens with a specific action, 'Start a tail', and precisely states what is returned: a cursor to poll from ({event_type, since_seq}). It clearly distinguishes this tool from a callback-based subscription and from poll_memory_events, so an agent can understand its role immediately.

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 explicitly says when to use this tool versus alternatives: MCP calls cannot be called back, so this returns a cursor; use poll_memory_events with the returned since_seq to receive events; use Inspeximus.subscribe() from Python for real callbacks. This is direct and actionable routing guidance.

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