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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses that the tool supports optional filtering and a multi-account parallel mode with specific pagination constraints. This adds behavioral detail about how accounts and pagination interact, which annotations do not cover.

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?

The description is compact, with two sentences covering purpose and key usage details. It front-loads the main function and adds special behavior in the second sentence. Could be improved by structuring the filter list for readability.

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?

Missing return value description, pagination details (beyond the restriction), and output format. With no output schema, the agent needs to know the shape of results, which is absent. Parameter semantics are also incomplete, making the tool harder to use accurately.

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?

With 0% schema description coverage, the description only enumerates parameter names (status, type, email, etc.) without explaining their meaning or expected format. For example, 'last4' and 'limit' are not defined, leaving ambiguity about their purpose and usage.

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 clearly states it lists corporate cards (credit) with optional filters, distinguishing it from sibling tools like contasimples_card_write_block which are write operations. It specifies the resource (corporate cards) and action (list), with a comprehensive list of filters.

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?

Provides explicit context on when to use the accounts parameter for parallel queries across companies, and a critical restriction that next_page_start_key cannot be used when accounts > 1, requiring per-account pagination. While it doesn't explicitly state when not to use the tool, the read-only intent and sibling naming make it clear.

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