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

Beyond the annotations, the description discloses critical behavior: delivery depends on the person's filters and platform rules, blocked messages return reasons and hints while the person never sees them, messages may be queued up to 7 days, and free usage is limited by trust level. These details materially improve an agent's ability to invoke the tool correctly and avoid violating platform constraints.

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 action and then adds operational detail. It is denser and longer than ideal, especially the enumeration of rejection reasons and free-tier limits, but those details are relevant to correct use and are not merely redundant with structured fields.

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 complex, open-world write tool with nested parameters and no output schema, the description is sufficiently complete: it explains delivery outcomes, failure reasons, queuing, usage limits, continuation behavior, response handling via get_conversation, and the docs link. An agent has enough context to call the tool and interpret the main outcomes.

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 high at 89%, so the schema already documents most parameters. The description still adds useful meaning by summarizing the structured offer fields, explaining message length and language expectations, clarifying that on_behalf_of company must be verified, and noting that continuation uses conversation_id plus message only.

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 uses a specific verb and resource: 'Start a conversation with a person in their Alion messages.' It clearly distinguishes a first structured offer from continuing an existing conversation via conversation_id, so an agent can identify the tool independently of its 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 strong contextual guidance: first messages are structured offers with a specific shape, continuation uses only conversation_id and message, and answers arrive via get_conversation and set_webhook. It also explains when delivery is blocked by filters/rules, though it does not explicitly direct users to prerequisite discovery tools such as search_people.

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