env_env_set

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

With no annotations, the description carries full burden. It discloses that the variable is visible to child processes and does not affect the parent shell. This is critical behavioral context. It does not mention error handling or return value, but an output schema exists.

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 purpose, no redundant text. Every sentence adds unique value about scope and effect.

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 the simple nature of the tool, the description covers essential behavioral aspects. An output schema likely documents return values, so completeness is adequate. Could mention if errors occur on invalid keys or overwriting behavior.

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?

Parameter names 'key' and 'value' are self-explanatory, but schema description coverage is 0%. The description adds no extra constraints or formatting details beyond the obvious, so it provides minimal added value.

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 clearly states the tool sets an environment variable for the current process, specifying verb and resource ('Set an environment variable'). It distinguishes from sibling tools like env_get or env_list by noting scope and effect on child processes.

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: use when you need to set an env var for the current process and its children. However, no explicit guidance on when not to use or alternatives (e.g., env_load for loading from files).

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