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

Annotations declare openWorldHint=true, readOnlyHint=false, destructiveHint=false, but the description goes beyond by adding crucial context: it explicitly states 'Never fabricates an entity not actually present in the source' (a key reliability guarantee), 'SPENDS your balance' (cost warning), and requires OAuth authentication. These are significant behavioral disclosures not in the 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, zero filler. Every sentence earns its place: entity list, anti-fabrication guarantee, cost/auth warning. Slightly dense use of ALL-CAPS emphasis, but information density is high and the warning about spending balance is critical for user decisions.

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 2-param tool with 100% schema coverage and an output schema present, the description adequately covers purpose, input handling, safety guarantees, and cost implications. Could theoretically mention the output format, but with an output schema present the description needn't explain return values. Missing minor items like pagination or size limits, but overall solid for its complexity level.

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 (source, budget_pence) are already well-described in the schema. The description adds the 'Never fabricates' guarantee which relates to source handling but doesn't add meaningfully beyond schema for parameters. Baseline 3 is appropriate given complete schema coverage.

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 specifies exact verb ('Extracts'), exact resources (email addresses, company names, dates), and scope ('verbatim in a document or URL'). The explicit list of entity types clearly differentiates it from similar extraction siblings like forcedream_extract_action_items, forcedream_extract_data, and forcedream_summarize_document.

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?

States what inputs are accepted (document or URL), which gives clear usage context. However, it doesn't explicitly exclude cases (e.g., doesn't say when NOT to use this vs extract_data). The 'Never fabricates...' line clarifies an important behavioral contract for correct selection, but no explicit alternative tool is named.

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