tariff-refund-screen

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

Annotations already signal read-only and non-destructive behavior. The description adds useful context about provenance (SEC filings, ASC 450-30, no XBRL tag) and the data's scope (one-time CSV of US-listed companies), which helps an agent understand what the tool is returning. No contradiction.

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 longer than strictly necessary but every sentence carries content: what the tool returns, what the screen is, and why it is useful. The main clause is front-loaded.

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 no-argument read-only info tool, the description gives enough domain context to understand what will be returned. It could be more explicit about output shape or the difference from get_tariff_refund_screen_preview, but these are minor given the tool's simplicity.

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?

There are no parameters, and schema description coverage is 100%, so there is nothing for the description to add at the parameter level. This is the baseline for a zero-parameter tool.

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 names a specific action ('Get details and pricing') and an unambiguous resource (Edge Thirteen's Tariff Refund Screen), then explains what that screen contains. It is clear, though it does not explicitly contrast with the sibling preview tool.

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 use case: investment research looking for a disclosure that cannot be surfaced by numeric screens. It does not explicitly mention the sibling preview tool or say when to choose info over preview, so it lacks exclusions and alternatives.

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

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

Annotations already mark it read-only and non-destructive, so the description adds access and boundary context: free, no key, top-10 only, same data as the tool page, and what the paid CSV does differently. This is useful beyond structured fields, though it doesn't cover output formatting or error behavior.

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 dense sentences, front-loaded with what the tool returns and immediately followed by the paid-CSV distinction. Every clause adds information and there is no filler.

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 no-parameter read-only preview, the description is complete: it names the output fields, the ranking basis, the data limitation (top 10), and the access condition. Since there is no output schema, the explicit field list effectively covers the return-value gap.

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?

The schema has zero parameters, so the baseline is 4. There are no parameters for the description to elaborate, and it doesn't invent any; the listed output fields are appropriately detailed given the empty input schema.

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?

States a specific action ('Get') and a precise resource ('free top-10 preview from the Tariff Refund Screen'), enumerates the returned fields, and clarifies it is the free preview rather than the paid CSV. This makes its scope obvious and distinguishable from the paid-data alternative.

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?

Explicitly differentiates this tool from the paid CSV: use the free preview here, and the paid CSV when the other 150 companies/citations/URLs are needed. It also states the access condition 'Free, no key.' The only unmentioned alternative is the sibling info tool, but the free-preview vs. paid-full-export choice is unambiguous.

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