rms_system_instructions

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

No annotations are supplied, so the description carries the full burden. It implies a pure retrieval operation by saying the tool 'returns' a protocol and 'lets an agent self-bootstrap', which suggests no mutation, but it never explicitly states that it is read-only, side-effect-free, or unauthenticated. It also does not describe the shape of what comes back (a markdown rule block, structured object, length), which matters for a tool whose entire value is its return payload.

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 its contents before the rationale. Nothing is wasteful, though the second sentence largely re-explains the first from the agent's point of view rather than contributing new operational detail.

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 zero-required-parameter retrieval tool with no output schema, the description covers what it does and roughly why. The remaining gap is the return format and whether the protocol differs by project, which would normally be covered by an output schema or annotations that are absent here.

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% for the single optional 'project' parameter, and the schema itself explains the fallback condition ('when the client sends no workspace root'). The description adds no information about the parameter, which is acceptable at full schema coverage, so the minimum-viable 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?

The description gives a specific verb and resource: 'Return the canonical RMS Memory usage protocol', and parenthetically names its contents (search-first, persist, session continuity). That clearly separates it from the sibling tools, which are all operational (rms_search, rms_read, rms_write, rms_prune, etc.) rather than documentation-retrieval. It stops short of 5 only because the phrase 'Lets an agent self-bootstrap' restates the same idea rather than adding a further distinction.

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?

There is an implied trigger: call this when no rule files are injected and the agent needs to bootstrap. But the guidance is conditional and passive ('Lets an agent self-bootstrap') rather than imperative, and it names no exclusions or alternatives (e.g., when the protocol is already in context, or whether rms_overview supersedes it). An agent must infer the when-to-use condition.

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