Query RCI tree

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes further by explaining WHY it cannot write (writing needs a POST body it never sends) and enumerating blacklisted scopes. This adds real context beyond the annotation flags.

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?

Front-loaded with the core behavior and safety claim, then supporting detail. The path lists are a bit dense but each entry is functional; little waste overall.

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?

With no output schema and only two simple params, the description covers safety, purpose, alternatives, and scope limits. It does not describe the shape of returned data, but for an exploratory raw-query tool this is nearly complete.

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 coverage is 100%, so both params are documented, and the description reinforces the config_tree purpose ('see write-shapes, e.g. ip/static'). The 'Useful paths' examples add practical guidance the schema doesn't, though it stops short of path syntax details.

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?

States a specific verb and resource ('Raw READ-ONLY query against the router's RCI tree') and the exact mechanism (GET /rci/show/<path>). It distinguishes itself from siblings by redirecting running-config to get_config, so an agent can separate it from the many get_* tools.

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?

Gives explicit when-to-use ('explore state that has no dedicated tool yet') and when-not (the blacklist: running-config, crypto, ppp, user), and names the alternative for the blacklisted case (get_config). Routing guidance is complete.

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