run_task

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

No annotations are provided, but the description discloses critical behavioral traits: it does not execute a shell or agent-provided command line, the target is restricted to one shell-safe argument, project-supplied commands require prior trust ('plumb trust'), and output/runtime are bounded. This goes well beyond what annotations would provide and fully informs the agent of boundaries and safety aspects.

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?

The description is concise, front-loaded, and every sentence earns its place: it states the purpose, constraints, trust requirement, and pairing with topology_affected. No filler or repetition of schema content; it is efficiently structured in a few dense sentences.

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 no output schema and two parameters fully described in the schema, the description is complete: it explains the tool's scope, exclusions, trust model, target restriction, output bounding, and complementary relationship with topology_affected. An agent has enough context to decide when and how to invoke it safely.

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 100%, providing baseline 3. The description adds meaningful parameter semantics beyond the schema: it explains that the slot maps to a configured command, and the target fills a {target} placeholder with one shell-safe argument (with a detailed character class). This reinforces and clarifies the schema without redundancy, justifying a 4.

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 starts with a specific verb+resource: "Run a stored per-language task command" and enumerates the exact facets (build, lint, test, e2e, verify). It clearly differentiates from sibling tools like run_command by stating "no shell, no agent-supplied command line", making its role unambiguous.

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?

Explicitly states when to use this tool vs alternatives: it runs only the user-saved command, not arbitrary agent-supplied commands, and pairs with topology_affected ("which says WHICH tests to run; this runs them"). Also notes the trust prerequisite for project-supplied commands, which is a concrete when-to-use condition.

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