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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-annotation information: pricing of $0.002 USDC per successful call via x402 (Base, Solana or Arc) with failed calls not charged — valuable for an agent deciding whether to call. It says nothing about rate limits, pagination beyond the limit cap, or latency, which are the remaining behavioral unknowns.

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 core content is front-loaded, but the whole tool description is a single run-on sentence stitched together with semicolons, which makes the two modes harder to parse than they need to be. The 'Related tools on this server' digression spends a full clause each on two Swedish/Norwegian registry tools that are far less likely confusions than the review directories, so that space is poorly allocated.

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 an output schema present, the description needn't explain return values, and the moderate complexity of a two-mode directory lookup is adequately covered: modes, filters, cost, and alternatives are all present. The only shortfall is that the closest competing tool is never named, which is the one thing that would prevent a wrong tool choice.

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 all four parameters are already documented with examples (slug example 'eleks', country code list, category values, limit range 1-48). The description reinforces that country is software-development-only and names the four categories, but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 the specific resource (IT service companies ranked on GoodFirms) and both operating modes: a ranked list filtered by category, or a single-company dossier looked up by slug. It also enumerates the returned fields for each mode, so an agent knows exactly what it gets. It only partially differentiates from siblings — it names two Nordic registry tools but never mentions the closest alternative, b2b_clutch_reviews, which is the same kind of review-driven agency directory.

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?

Mode selection is clear from the phrasing: 'by its GoodFirms slug' for a dossier versus category/country for the ranked list, and it notes country filtering applies only to software development. It also explicitly routes the agent away to two sibling tools with 'when you need' conditions. What's missing is any exclusion against the genuinely similar review directories (clutch_reviews, g2_software_categories, angies_list), leaving the most likely mis-selection unaddressed.

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