kernel_agents_memory

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

With no annotations, the description must carry the behavioral burden; it does establish that this is a read and that it can reach another agent's interactions, which implies cross-agent read access. It says nothing about permission requirements, what happens with an unknown agent_id, or how far back "recent" extends beyond the limit parameter.

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?

Two short sentences, front-loaded with the resource and then the usage cue, with no redundant restatement of the name or schema. Every clause earns its place.

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 simple two-parameter read tool with no output schema, the description covers what is read, whose memory it is, and why to call it. The remaining gap is the shape and ordering of returned messages, which an agent would need to interpret results 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 coverage is 100%, so both agent_id and limit (default 10, max 100) are already documented. The description adds only the qualifier "recent," which hints at recency ordering but does not explain ordering or what a message record contains, so the baseline of 3 applies.

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?

"Read an agent's conversational memory" names a specific verb and resource, and the follow-up clause defines what that memory contains (recent interactions with humans and other agents). It does not differentiate from siblings such as kernel_agents_history or kernel_agents_inbox, so an agent must infer which is the right memory surface.

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?

"Use this to check what another agent has been working on or said recently" gives a concrete trigger for calling the tool, which is clear situational guidance. It offers no exclusions or named alternatives, so there is no help when the agent needs to choose between this and a sibling read tool.

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