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

Annotations already declare read-only/non-destructive, and the description adds substantial context beyond them: the 100-item cap, soonest-due-first ordering, totalOpen/truncated signals for overflow, and the meaning of 'resolved'. This is exactly the kind of behavioral detail annotations cannot convey.

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?

Front-loads the resource scope and is largely free of waste, though the item-contents enumeration is dense. Dense but earns most of its space given the return structure being described.

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?

With no output schema, the description carries the full burden and does so, explaining the shape of each item (draft text, client, severity, type, status, assignee, due date, note) plus truncation behavior. Nothing an agent needs to call it correctly 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 coverage is 100% and both parameters are already documented in the schema, so the description doesn't need to carry that load. It only loosely nods to the draft text and the 100-item cap without adding syntax or format detail beyond the schema—baseline 3 is appropriate.

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?

States a specific verb and resource: the Approvals queue containing AI drafts awaiting a person plus teammate-created manual tasks. It explicitly routes the decision action to decide_approval, making it distinguishable from that sibling without opening either schema.

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?

Says what this lists and names the alternative ('decide_approval approves or dismisses one'), giving the agent a clear read-vs-act split. The 'open or in progress' scoping further refines when this tool applies.

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