send_message

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

With no annotations, description fully discloses irreversibility, visibility, and lack of recall via API. No contradictions.

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?

Efficient structure: purpose, warning, args, returns. No wasted 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?

Covers input, behavior, irreversibility, and output format. No output schema needed since return is described. Minor omission of rate limits or error handling.

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 0%, but description adds: chat as 'id/@username/title', text as 'Non-empty message text'. Provides useful semantics beyond 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?

Clear verb-resource-context: 'Send a text message to a chat as the logged-in user.' Distinguishes from siblings like send_file or download_media.

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?

Warns of irreversible action: 'confirm the chat and text before calling.' Lacks explicit when-not or sibling comparison but adequately implies usage context.

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