mnemosyne_agent_list

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

The readOnlyHint=true annotation is confirmed and enriched by the description's 'Metadata only' and 'reads' language. More importantly, the description discloses non-obvious behavior beyond the annotation: it 'reads every harness installed here,' it works 'with the Mnemosyne OS app closed,' and it exposes the critical caveat that 'a crashed session and an idle one fall equally silent, so nothing here can tell you an agent is working' — telling the agent it must draw the liveness conclusion itself, not the tool.

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 longer than minimal but every sentence earns its place: the core function leads, followed by the metadata list, the cross-harness scope, the usage trigger, the silent-session caveat, and the app-closed note. It is front-loaded with the primary purpose and well-ordered, though the metadata enumeration and caveat sentences could arguably be tightened without losing meaning.

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 filterable listing tool with three well-documented parameters, no required params, and no output schema, the description covers the essential ground: return metadata fields, scope, usage timing, and the liveness limitation. One minor gap is that the exact response structure isn't formally specified, but the description's metadata field list substantially compensates for the absent output schema.

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 100%, so the baseline of 3 applies — the schema already documents limit, project, and live_only clearly, including the per-harness semantics of limit. The description only loosely reinforces this by mentioning 'how many files were touched' and 'when a line was last written,' which map to the live_only window, but it adds no new parameter syntax or format details beyond the schema.

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 states a specific verb and resource: 'List the other coding-agent sessions on this machine, read from the transcript files their harnesses already write to disk.' It enumerates exactly what metadata is returned (conversation name, project, git branch, model, last tool, files touched, last-write time) and scopes itself clearly ('Metadata only', 'every harness installed here, not just your own'). This distinguishes it from siblings like mnemosyne_agent_files and mnemosyne_agent_collisions without needing their schemas.

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 gives an explicit when-to-use directive: 'Use it before you touch shared state.' It also explains the value proposition contextually ('you can see a session from a different agent working in your repository'). It does not name sibling alternatives or state when-not-to-use, but the practical trigger is clear and actionable.

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