Feed Preflight

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

Annotations already declare read-only, idempotent, closed-world, non-destructive behavior, so the bar is lower. The description still adds real value beyond them: the 20-record cap, the guarantee that no URLs are fetched, and that input is not stored — all relevant to a privacy-sensitive validation call.

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 short sentences, front-loaded with the operation and scope, then data-handling constraints. Nothing repeated and nothing that does not earn its place.

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 one-parameter, no-output-schema tool with rich annotations, the description covers purpose, limit, and data-handling guarantees. The remaining gap is that 'structural issues' is never concretized — the agent cannot tell what counts as an issue or what the response contains.

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 carry the 'csv' parameter alone. It adds meaningful constraints (product records, max 20 rows, redacted content) but never specifies shape — header row, delimiter, required columns, or how malformed input is treated within the 32,000-character limit.

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?

Specific verb + resource + scope: 'Check up to 20 CSV product records for structural issues' tells the agent exactly what operation runs and on what. The single sibling (get_purchase_link) is unrelated, so no explicit differentiation is required, but the description never states that it returns a report rather than fixing anything.

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?

Gives a clear operating context (structural validation of product CSV records) and a hard usage constraint: send only redacted data, no personal or secret fields. No alternative tools are named, but with only one unrelated sibling there is nothing to route between.

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 declare readOnly, idempotent and non-destructive, so safety is covered. Beyond that the description only gestures at a 'paused sales status' and says a purchase link is absent – it does not explain what state triggers 'paused', what the response contains, or whether the absence of a link is an error case.

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 short sentence with no padding, which is appropriate in size. However, the phrasing is awkward and puts the ambiguous qualifier 'without a purchase link' in the most prominent position, so brevity comes at the cost of clarity.

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?

With no output schema, the description is the only source of information about the return value, and it never says what the status object or value looks like or what 'paused' means operationally. For a zero-parameter read whose entire value is its output, this leaves the agent guessing.

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 tool takes zero parameters and the schema is fully closed (additionalProperties: false), so there is nothing for the description to disambiguate. Baseline 4 applies.

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 sentence names a resource loosely ('paused sales status') but the verb framing and the phrase 'without a purchase link' are ambiguous – it reads like a tool that deliberately omits data rather than one that fetches a status. An agent cannot confidently tell what this returns or how it differs from check_feed.

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?

There is no indication of when to call this versus the sibling check_feed, no prerequisites, and no exclusions. The only hint ('without a purchase link') is phrased as a property of the result, not a usage rule.

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