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

The annotations already indicate destructive, non-read-only, non-idempotent behavior, so the bar is lower. The description adds useful behavioral context by specifying the success/error return shape and the need to source ability_name from discover_abilities. It does not elaborate on side effects, but annotations cover the main safety signal.

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 two sentences with no filler. The core action is front-loaded, followed by precise parameter instructions and a compact return-format note. Every sentence earns its place.

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?

The description is largely complete for a dynamic execution tool: it names the discovery prerequisite, defines parameter shaping, and gives the return contract. It does not explicitly warn about arbitrary or destructive abilities, but the annotations already carry destructiveHint=true, and the open-world nature is reinforced by referencing discover_abilities.

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 only 50% because ability_name lacks a description. The tool description compensates fully by explaining that ability_name must come from discover_abilities and that parameters must follow that ability's own input schema, including the {} convention for no-argument abilities.

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 clearly states 'Run one ability on the site', identifying both the action and the resource being acted on. It also references discover_abilities, which helps distinguish this execution tool from the discovery and info siblings.

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 description gives concrete usage guidance: pass the exact ability_name from discover_abilities and shape parameters according to that ability's input schema, using {} when none are needed. It stops short of explicitly naming alternatives or stating when not to use this tool, but the execution vs. discovery/info distinction is strongly implied.

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