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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it clarifies the tool does NOT acknowledge directives and that a separate action (ack_attention_directive) is required. It also scopes the result to 'THIS operator' and notes optional filtering, which is useful behavioral information not present in 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?

Three sentences with zero waste. The core purpose is front-loaded, the optional filter is mentioned, the intended audience is stated, and the critical non-ack behavior is called out. Every sentence earns its place.

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 read-only list tool with no output schema, the description covers the essential aspects: what it lists, for whom, optional filtering, and the critical distinction from ack. The only minor gap is that it doesn't describe the return format or pagination behavior, but given the readOnlyHint and idempotentHint annotations, this is not a significant omission. The description is complete enough for an agent to call it correctly.

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 three parameters (limit, companyId, target_session_id). The description adds the semantic context that target_session_id filters 'pending directives for this session id' and that companyId is for 'company-scoped tools', but these largely mirror the schema descriptions. The description does clarify the default scope ('THIS operator') which helps interpret the absence of required parameters, but it doesn't add substantial new meaning beyond the 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?

The description states a specific verb ('List'), a specific resource ('pending attention directives'), and a scope ('for THIS operator'), which clearly distinguishes it from the sibling ack_attention_directive and cancel_attention_directive. It also names the intended users (Hosts/CoS), making the purpose unambiguous.

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 explicitly says when to use it ('to see what is waiting') and what not to do ('Does not ack — use ack_attention_directive after acting'). This directly routes the agent to the correct sibling tool, providing both positive and negative usage guidance.

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