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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable behavioral context: the exact fields returned (applicationId, status, tier, cohort, purpose, requestedAmount, term, decision timestamps), the countByStatus rollup, the non-paginated summary nature, and the auth requirement (Bearer token via two-header model, merchant-or-operator JWT). This goes beyond annotations and aids safe invocation.

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, each earning its place: purpose+return, use case, auth. No filler or redundant restatements of the name or schema. Front-loaded with the primary 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 read-only list endpoint with no output schema, the description covers the return payload, use case, and auth. It lacks details on error conditions or the exact meaning of 'two-header model,' and does not contrast with get_lender_history. However, it is sufficiently complete for a tool with simple parameters and strong annotations.

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 0%, so the description must compensate for parameter meaning. It does not. The parameters merchantId and agentBearer are not explained; merchantId is only described by a regex pattern in the schema, and agentBearer's connection to the 'two-header model' is ambiguous. The description mentions auth but does not map it to the agentBearer parameter, leaving the agent underinformed.

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 clearly states the tool's function: 'List a merchant's lending application history.' It identifies the specific resource (merchant lending applications), the action (list), and provides details about the returned data (compact summaries, countByStatus). It distinguishes from siblings like get_lending_application_status by emphasizing full history and compact rollups.

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 clear usage context: 'Used by lender-agents to surface a merchant's application history without paginating raw rows.' This tells when and why to use the tool, implying it replaces a paginated raw list. It does not explicitly mention alternative tools or exclusions, but the context is clear enough.

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