compute.plan_environment

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

Annotations already declare readOnlyHint=true, but the description adds concrete meaning: "nothing is installed and no directory is created", telling the agent exactly which side effects are absent. It also discloses the shape of the result (commands, packages, network needs, ownership verdict), which is valuable given there is no output schema. It stops short of describing permissions or prerequisites.

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 sentences, front-loaded with the action and outcome list, then a single clarifying constraint. No filler or 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?

With no output schema, the description usefully previews the four things the plan returns, and the read-only guarantee covers the main behavioral risk. The remaining gap is identifier semantics for the two required parameters, which neither schema nor description resolves.

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 0% for both required parameters, so the description must carry the load. It only implicitly maps node_id via "on one node" and env_id via "environment"; it never states what an env_id or node_id looks like, whether they are names or opaque identifiers, or where to obtain them (e.g., compute_list_environments / compute_list_nodes).

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 ("Plan how to create or complete") plus the resource ("an environment on one node") and enumerates the plan contents: commands, missing packages, network needs, ownership verdict. An agent can distinguish it from compute_apply_environment or compute_inspect_environment by the word "Plan", though no sibling is named explicitly.

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 implied rather than stated: "Plan how to create or complete an environment" suggests a dry-run step before applying, and the read-only sentence reinforces that. However, it never says when to prefer this over compute_inspect_environment, compute_verify_environment, or compute_apply_environment, leaving the agent to infer the workflow position.

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