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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds genuinely useful behavior the agent could not otherwise know: balance charges (about a cent per 20 Google Maps reviews), Glassdoor being billed and capped at 10 with a possible pending job returning job_id and next_read.link, storage in Puley history, consumption of one read, and a no-reviews-no-charge guarantee. Employee identity exclusion is also disclosed. Nothing here conflicts with the non-read-only, non-idempotent 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?

The content is high-value with little filler, but it is delivered as two long comma-spliced run-on sentences (the opening is a fragment) rather than a structured list of sources, costs, and return fields. It would read far better as a short lead sentence plus per-source bullets.

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?

There is no output schema, yet the description covers return fields (stars, title, text, date, app version), the star split and Trustpilot summary, async job handling, billing, history persistence, and refund behavior. For a three-parameter, multi-source tool this is close to complete; only the 'source' string contract remains underspecified.

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 coverage is 0%, so the description carries the full burden and largely does: it specifies accepted source formats (app name, store link, website like temu.com, Google Maps/Hellopeter link), the limit range of 10–200 with the Glassdoor 10-review exception, and that country applies only to app-store lookups when an app is named. The only gap is that the free-form 'source' string has no explicit format contract beyond examples.

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 verb+resource (fetch recent reviews in bulk, with star split) and enumerates the exact source families it covers: App Store/Google Play apps, Trustpilot companies, Hellopeter businesses, Google Maps places, and Glassdoor company links. It is clearly not find_news or read_comments, though it never names a sibling to sharpen the distinction.

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 per-source conditions, e.g. Trustpilot data is 'for judging whether a shop or company is trustworthy' and each source must be passed as a name, website or link. However, there is no explicit statement of when to prefer this over read_comments, company_brief, or is_it_real, so routing between siblings is left to inference.

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