list_agent_variables

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

Annotations already cover safety (readOnlyHint, idempotent, non-destructive), but the description adds a genuinely useful behavior: values where isEnv is true are masked. That is non-obvious and prevents an agent from expecting real secrets. It stops short of describing ordering or response shape, which keeps it below 5.

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?

Three tight sentences, front-loaded with the purpose, then scope exclusion, masking caveat, and alternative. No padding, and the most decision-relevant information comes first.

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?

For a one-parameter read-only list call, the description covers purpose, scope exclusion, masking behavior, and the alternative path. Remaining gaps are minor: agentId format and return ordering, though the absence of an output schema makes the latter a smaller omission.

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?

There is one required parameter (agentId) with 0% schema description coverage, so the description must carry the burden. 'On a Convocore agent' implies agentId identifies the target agent, but no format, source, or constraints are given beyond that implication.

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 ('List') and resource ('variables on a Convocore agent'), then defines what those variables are (env/global/system keys used in prompts and tools). It also explicitly carves itself away from MCP variables, so an agent can tell what this tool does and does not return without opening the schema.

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?

The 'Not MCP variables' exclusion and the pointer to interact_with_agent with variablesOverrides / initNodesOptions for trial overrides give explicit when-and-when-else routing. An agent knows both the correct scope for this tool and where to go when it wants to inject overrides instead of merely listing.

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