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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered; the description still earns credit for the non-obvious disclosure that execution is offline by default absent operator-granted network access. "Does not change the function" largely restates readOnlyHint but usefully confirms side-effect freedom for a tool that executes code.

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 short sentences, action front-loaded, with the two most decision-relevant caveats (no mutation, offline) trailing economically. Nothing redundant enough to cut.

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, no-output-schema tool with rich annotations, the description covers action, side effects, and network posture adequately. It stops short of saying what a failing test or an unconfigured-sandbox response looks like, which would help an agent interpret results.

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% and the single functionId parameter is documented with a pointer to agent_functions_list, so the schema carries the load. The description only says "one Code function's saved tests" and adds no format or discovery detail beyond that.

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 ("Run one Code function's saved tests in the sandbox") plus the return shape ("return each result"), which cleanly separates it from siblings like agent_functions_get_code or agent_functions_create_code that touch code rather than execute tests.

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 (verify a saved function via its tests) but never spelled out as when-to-use versus an alternative, and no prerequisites such as needing saved tests to exist are stated. The only explicit guidance is the network condition, which is a constraint rather than a routing rule.

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