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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description reasonably spends its words on what comes back: title, tier, report counts, first/last report dates, listing date, summary, lead-vs-idea-report type, price, sale counts and page. That is valuable given there is no output schema. It loses a point for never defining what 'biggest' orders by (report count? price?) and for not mentioning that results are paginated.

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 purpose clause is front-loaded, which is good, but the return-field inventory is a single unbroken sentence of roughly sixty words strung together with commas, which is hard to scan. A short bulleted or semicolon-grouped field list would have made the same content far more usable without adding length.

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 and four optional params, the description needs to say what a record contains, and it does so thoroughly, including the commercial fields (price, sale counts) that shape interpretation of max_sold. What is still missing is the meaning of the sort key and any note on pagination size, both of which matter for a list tool driven by a cursor.

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 100%, so cursor, query, kind and max_sold are already fully documented; the baseline is 3. The description reinforces the lead/idea_report distinction and the notion of sales counts behind max_sold, but adds no format or behavior detail the schema does not already carry.

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?

Gives a specific verb and resource: 'Search the problems people have that Triremes lists', plus the ordering ('biggest first'). It does not reference any sibling (get_website_gap_score, search_website_gaps, show_samples), so the agent gets no explicit disambiguation, but the object of the search is distinct enough to separate it in practice.

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 statement of when to reach for this tool versus the website-gap or sample tools, and no prerequisites or exclusions. Usage is only inferable from the phrase 'problems... that Triremes lists', and the closing sentence about buying on the page is commercial context, not invocation guidance.

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