Send Message

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds rich behavioral context: profile-based send may create a separate DM even after inspecting a thread; recipient must be directly messageable; it falls back to connect_with_person; authorization requires validating a recipient-specific Message action and following browser navigation; contradictions fail closed; no private API is used; and it is a write operation when confirm_send is True. These details go well beyond the annotations.

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 front-loaded with the core purpose, then expands into critical safety and usage caveats. It is longer than typical but every major section addresses a distinct concern (reply vs new DM, recipient eligibility, authorization, write condition). There is minor repetition around 'not a reply path,' but overall it is well-structured and earns its length.

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 the tool is a write operation with open-world and destructive implications, and an output schema already exists to explain return values, the description covers all necessary context: what it does, when to use it, when not to, how recipient authorization works, fallback behavior, and the confirm_send condition. Nothing critical for correct invocation is missing.

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%, so the schema already documents all four parameters in detail. The description adds some contextual meaning (e.g., confirm_send being required for write, profile_urn used for verification) but does not provide syntax, format, or additional semantic constraints beyond what the schema already states. The baseline score of 3 is appropriate when the schema carries the parameter documentation.

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 explicitly states the specific verb and resource: 'Compose and send a new message to a LinkedIn user.' It also distinguishes this tool from thread-reading siblings by clarifying it is not a reply path for existing conversations. An agent can immediately tell what this tool does and how it differs from get_conversation or search_conversations.

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 explicit when-to-use guidance (profile-based targeting to send a new message), when-not-to-use guidance (not a safe reply path; do not treat as a reply), and alternatives (use connect_with_person first if no Message action, and note that get_conversation/search_conversations only read threads). This is a complete routing guide.

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