mnemosyne_agents

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

With no annotations, the description carries the behavioral burden, and it excels: it discloses that only metadata is returned, that all harnesses are read, that 'working' status is never reported, that silence means either crashed or idle, and that it works with Mnemosyne OS closed. These are non-obvious behaviors that materially affect how an agent interprets results.

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 front-loaded with purpose and scope, then moves to return fields, usage, the critical caveat, and an environment fact. Each sentence adds information that is not inferable from the schema or tool name, with no filler or repetition.

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 read-only metadata tool with no output schema and no annotations, the description covers the essential ground: input semantics, return field list, cross-harness scope, when to use it, how to interpret liveness, and an environmental constraint. There are no obvious gaps that would cause an agent to misuse it.

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?

The schema already documents all three parameters, so the baseline is 3. The description adds meaningful interpretation: the limit is per-harness with a rationale, the project filter is meant for repository-folder scoping, and live_only relies on a recency window printed in the answer.

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 subject—other coding-agent sessions on this machine—and clearly states the source (transcripts harnesses write to disk) and the deliverable (metadata only). It also distinguishes itself by saying it reads every installed harness, not just the agent's own, which separates it from the agent-related sibling tools.

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 an explicit trigger: 'Use it before you touch shared state,' and explains the cross-agent visibility that makes it relevant. It does not name alternative sibling tools or state when not to use it, so it stops short of full usage branching, but the context is clear.

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