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

Annotations provide no safety/behavior coverage (all hints false), so the description carries the burden. It discloses the internal nature and customer exclusion, but does not describe permissions, persistence, or result behavior beyond posting. Adequate but not rich.

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?

Three short sentences, each adding value: purpose, use cases, and exclusion. No redundancy, front-loaded with the core action.

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 tool with 4 params (one nested) and an output schema, the description covers key usage context and boundaries. It could mention metadata handling or participant requirements, but the schema covers parameter specifics and the output schema exists.

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 descriptions cover 100% of parameters, so the baseline is 3. The description adds no additional parameter-level detail beyond what the schema already provides; it only implies content may include source links.

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 names the specific action (post), the object (internal message), the destination (Workroom thread), and the actor (AI colleague). It also distinguishes from customer-facing messaging by saying 'does not send anything to customers.'

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 provides explicit use cases: report findings, ask owner for approval, share source links after reading CRM/Inbox data. It also states a clear exclusion (does not send to customers). However, it does not name alternative tools for comparison, so it falls short of the full 'when not to use' guidance.

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