run_tool

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is covered structurally; the description's genuinely additive content is that some target tools are destructive and need confirm=true. It does not mention that wrapped calls can mutate state despite the outer tool's destructiveHint=false, nor how results/errors are surfaced. Note the mild tension with destructiveHint=false, but the annotation describes run_tool itself, not its payloads, so this is not a strict contradiction.

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 short sentences, front-loaded with the action and the discovery pointer, with zero filler. It is arguably under-specified rather than over-long, but nothing is redundant.

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 generic dispatcher with an open-ended nested params object and no output schema, the description needs to explain the indirection contract (discover schema, pass params verbatim, confirm for destructive targets). It covers the confirm rule and points to discovery but leaves return format and error handling unstated.

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 0% for two required params (name, params object), so the description must compensate; it does partially by implying 'name' is a tool name resolved via list_tools/describe_tool and that 'confirm' belongs inside params. It never states the params object must conform to the target tool's schema, nor how nested/arbitrary properties are validated.

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 a utility tool') and routes the agent to list_tools/describe_tool for discovery, which distinguishes it from the concrete sibling tools. It stops short of 5 because 'utility tool' is never defined and it doesn't state what a utility tool is versus e.g. plan_edit or render_preview.

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 parenthetical '(see list_tools/describe_tool)' implies the discover-then-run workflow, and the confirm=true rule gives one concrete precondition. However, it never says when an agent should use this dispatcher instead of calling a capability directly, nor what to do when a named tool is unknown.

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