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

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotent, so the safety profile is covered. The description adds genuinely useful context beyond that — sandbox isolation, a 'short' program constraint, and that it can invoke external_* functions — but says nothing about what the destructive risk actually is, time or size limits, or auth requirements.

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, no padding, and the core action is front-loaded before the pointer to server instructions. The deferral sentence is short but transfers substantive information out of the definition, which is the only thing keeping it from a 5.

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 values need no explanation. However, for an open-world, destructive, non-idempotent code-execution tool, the definition leaves the agent without any operating constraints (what 'short' means, sandbox limits, side-effect boundaries) and relies on server instructions the agent may not have surfaced.

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 a single parameter with 100% schema description coverage; the schema already explains that the code is a program body, that search_tools-declared external_* functions are callable, and that it must return its result. The description restates the same points without adding syntax, limits, or examples, so the baseline 3 applies.

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 (run) and resource (a short TypeScript program), plus the scope (orchestrating BioFlow MCP tools in an isolated sandbox). It also implicitly separates itself from the sibling by noting tools are discovered via search_tools, so an agent can tell the two apart without opening either 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?

Usage is only implied: the phrase 'orchestrates BioFlow MCP tools (found via search_tools)' suggests this is for multi-tool composition, but there is no explicit when-to-use vs. calling tools directly, and no exclusions. The instruction to 'See the server instructions for the full contract' explicitly offloads the guidance elsewhere rather than providing it here.

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