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

Annotations declare readOnlyHint=false, destructiveHint=false. The description crucially discloses that the call SPENDS user balance and requires OAuth authentication — valuable cost/behavioral context not in annotations. It also states empty-array return behavior. This adds meaningful transparency beyond what the structured annotations provide, though it does not detail any other side effects or rate limits.

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?

Two sentences, front-loaded with the core purpose and scope, then key side effects (spend/auth) and empty-array behavior. The budget_pence parameter is mentioned in schema but not description — arguably fine. No wasted words; could optionally include budget semantics but not required.

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?

Tool has 2 simple params, 100% schema coverage, and an output schema, so description doesn't need to detail returns. It covers the essential behavioral facts (spend, auth, empty-array). The main gap is the lack of explicit usage guidance relative to sibling extract_* tools, but given the tool's self-evident purpose and full schema coverage, this is reasonably complete.

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% — both params (source, budget_pence) are documented in the schema. The description adds scope about 'document or URL' which reinforces source semantics but doesn't deeply augment parameter meaning beyond the schema. Baseline 3 is appropriate since the schema already carries the weight.

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?

Description uses specific verb+resource ('Extracts concrete next-step or action strings') and clearly states scope ('stated or implied in a document or URL'). The empty-array behavior for no matches further clarifies. Distinguishes from siblings like extract_entities (different semantics: actions vs entities) and summarize_document (different output type).

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 does not explicitly state when to use vs alternatives, but the tool name 'extract_action_items' is self-descriptive among siblings. However, it does NOT specify exclusions or when-not-to-use. The 'per document or URL' scope is clear, but no distinguishing guidance from extract_entities/extract_data is given. Costs (SPENDS balance) and auth requirements are noted, which helps agent decide when to invoke.

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