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

Annotations declare readOnly/idempotent/non-destructive, and the description adds operational traits those don't cover: calls are stateless with cwd resetting to /, output is truncated at 30 KB, and nothing executes on a real machine. It even names the concrete spec path (/openapi/https://api.cpln.io/openapi.json), which is behavioral context an agent cannot infer.

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 what the tool is before any command syntax, then proceeds through read/search/explore idioms, a routing rule, and the two constraints (statelessness, 30 KB cap). Every sentence carries distinct information with no redundancy.

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?

An output schema exists, so return formatting need not be described. Combined with the statelessness note, the 30 KB truncation warning, the spec path, and path-discovery guidance, an agent has everything required to invoke this correctly on the first attempt.

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?

One parameter with 100% schema coverage, so the schema already documents the command string and supplies its own examples. The description's command idioms (head, rg -il, tree) largely restate the schema examples; it adds the tactical advice to prefer head and rg -C over cat due to truncation, but not enough to exceed the 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?

States a specific verb (read-only shell) over a specific resource (a virtual filesystem of Control Plane .mdx docs and OpenAPI specs) and immediately clarifies scope with 'nothing runs on a real machine', which disambiguates it from every mutating sibling like delete_resource or create_workload.

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 guidance with concrete idioms: read via head -120, search via rg -il, explore via tree -L 2. It also states a rule and the alternatives that satisfy it – 'Never guess a path: find it with search_control_plane, tree, or rg' – routing the agent to search_control_plane when appropriate.

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