rms_graph

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

With no annotations, the description carries the full burden and does add meaningful behavioral detail: mutations require explicit `project`, ensure only reconciles when empty or `force=true`, path uses BFS, and semantic edges are ephemeral. It does not disclose return shapes, side effects, or error behavior, but the key operational traits are present.

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 a single dense paragraph, but every clause earns its place: the operation type, action list with key semantic annotations, mutation requirement, and usage guidance. It is front-loaded and efficient, though the packed action list is somewhat hard to scan.

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?

Given 19 parameters, 10 actions, and no output schema, the description gives a solid action overview but not full contextual completeness. It lacks action-specific return expectations, node/edge key format guidance, and sequencing advice such as 'call status first,' leaving the agent to infer some behavior from parameter names.

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 is 3 and the schema already documents all 19 parameters. The description adds some grouping value by associating actions with relevant parameters and flagging `project` as required for mutations, but it does not substantially compensate 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 opens with a clear verb-resource pair ('Query and mutate the durable Markdown/code knowledge graph') and then enumerates the specific actions. It also distinguishes itself from the search siblings by stating it is for dependency traversal, so an agent can tell it apart from rms_search and rms_code_search.

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 explicit usage context: 'Prefer this for dependency traversal instead of guessing from search alone,' which names the alternative and the condition for choosing it. It does not enumerate when not to use the tool or contrast with the other siblings like rms_read or rms_write, so it stops short of a full 5.

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