rms_hygiene

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

With no annotations, the description carries the full behavioral burden and does well: it declares 'Never edits the vault,' specifies the 14-day and 90-day staleness windows, and describes the similarity approach. It stops short of details like permissions, output format, or how 'next steps' are produced.

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 compact sentences, front-loaded with the read-only nature and report contents, followed by the exact action alternative. Every clause contributes useful information.

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 two-parameter, read-only tool with no output schema, the description covers safety, scope, staleness thresholds, and the correct follow-up action. It could be slightly more complete by describing what the report output looks like, but nothing critical for correct invocation is missing.

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 both `project` and `min_similarity` are already fully documented, including the default and range. The description adds no parameter-level detail beyond what the schema provides, which is the expected baseline.

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 uses a specific verb and resource ('Read-only memory hygiene report for one project') and enumerates exactly what it surfaces: near-duplicate notes, stale checkpoints, and old session notes. It also distinguishes itself from the write path by naming `rms_write` + `supersedes` for merging, so an agent can identify its role without reading 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?

Usage is clear: run this for a read-only diagnostic and use `rms_write` with `supersedes` when actually merging duplicates. It does not explicitly compare itself to `rms_prune` or `rms_doctor`, so the routing guidance is good but not exhaustive.

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