mnemosyne_agent_files

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 so well: it discloses that file contents are never returned, explains provenance semantics (`recorded` vs `from a command` and the possibility that the command never completed), and states the output scope (session, agent, paths, timestamps).

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 main purpose is front-loaded, and caveats follow in a logical order. There is slight redundancy between 'with the session each came from' and later 'each line names the session and the agent it came from', which prevents a perfect conciseness score.

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 tool with no output schema, the description is complete: it tells the agent what to expect (sorted paths/timestamps, provenance, no contents), how broadly it searches, and when to use it. There are no required parameters and the schema covers optional ones.

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 applies. The description adds no parameter-level detail beyond reinforcing the general use case; it does not explain `limit`, `project`, or `contains` beyond the schema. This is acceptable because the schema fully documents them.

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?

Description opens with a specific verb and resource: 'Which FILES other agent sessions have written or edited recently'. It adds delimiting constraints ('Paths and timestamps only — never file contents', 'newest first', 'spans every installed harness') that make it clearly distinct from content-search or git-history siblings.

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?

Ends with an explicit use case: 'Use it to see what another session has already touched before you edit the same area.' It does not name alternatives or state when not to use it, but the intended context is clear enough for an agent to select it appropriately.

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