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

Adds substantial context beyond annotations: the reply is asynchronous and human, the Support team is notified, and the user must call read_support afterward. The annotation profile already covers write/open-world/non-idempotent safety, and the description usefully explains the real-world consequence.

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?

Four short sentences, front-loaded with the action and outcome, then the follow-up instruction and content guidance. Every sentence contributes operational information without repetition.

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, non-complex tool with no output schema, the description provides the essential action, side effect, async follow-up, permission note, and parameter intent. Nothing critical is missing for correct invocation.

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%, so the description must carry the meaning of text. It does so by saying text should contain what is needed and what was already tried, which is useful content guidance beyond the bare string schema.

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: writes a message into the user's Widely Support chat and notifies the Support team. It also distinguishes the follow-up path by naming read_support, so the agent can separate this from the reply-reading sibling.

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?

Explains the interaction flow clearly: send the question here, then use read_support for the human reply. It also guides what to put in text, though it does not explicitly compare against alternatives like search_help or send_message.

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