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

Annotations cover read-only/idempotent/open-world safety, so the bar is lower, but the description adds genuinely non-structured context: this call is free, requires no wallet or payment, takes no arguments, and returns a representative sample rather than real query results. That cost/payment and static-sample behavior is not derivable from 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?

A single sentence front-loaded with the [FREE] tag and the tool's identity, then the reason and the friction-free terms. Every clause carries information and nothing is padded.

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 zero-arg preview with no output schema, the description tells the agent what comes back (a sample response showing the shape) and that no inputs or payment are needed. It does not describe the sample payload's contents, which is a minor gap given there is no output schema to fall back on.

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?

Zero parameters and 100% schema coverage, so the baseline is 4. The description reinforces this with 'no arguments needed,' aligning with the empty properties object and preventing an agent from inventing query inputs.

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 states a specific deliverable: a sample response for edgar_fulltext_search (SEC EDGAR full-text search), so an agent understands it returns preview data rather than live search results. It differentiates itself from the paid sibling by the [FREE] marker and the 'before paying 0.02 USDC' framing. What full-text search actually does is only implied via the parenthetical, but the preview contract is unambiguous.

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?

It gives a clear context for use: inspect the response shape before committing 0.02 USDC, and notes no wallet/payment/arguments are required. The implicit alternative (use edgar_fulltext_search once you're ready to pay) is not named explicitly, so it stops just short of full when/when-not guidance.

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