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

No annotations exist, so the description carries the full burden. It does disclose several non-obvious traits: the data source ("Official CH data"), hard bounds (1-7 days, ≤40), and that the call is paid ($1.00 USDC), which is essential for an agent to know before invoking. However it says nothing about payment mechanics, whether partial/empty results are common for narrow SIC+postcode combos, or failure behavior, so the disclosure is partial for a paid, unannotated tool.

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 most decision-relevant facts (what it returns, the constraints) are front-loaded, and there is no filler prose. Slight waste in restating the same feed twice ("uk_leads_feed $25/30d" and "/uk-leads-feed $25") and in the telegraphic price abbreviations, which cost a little comprehension for little gain.

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 5-parameter, unannotated, no-output-schema tool, the description covers source authority, result caps, time window, and price - the essentials for deciding to call it. It is still incomplete on the return payload (does each lead include director names and addresses?), the payment flow implied by "$1.00 USDC", and parameter interaction rules.

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 must compensate, and it partly does: it identifies sic, location, and postcode_area as the filter dimensions and supplies the numeric bounds the schema lacks (days 1-7, limit ≤40). It still gives no format guidance for sic (4-digit code? partial match?) or location (city name vs. region), and never states that all five parameters are optional or how they combine.

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?

"Use this for UK new-incorporation leads with active director names" states a specific resource and scope (new incorporations within 1-7 days, active directors only), which an agent can distinguish from the officer-search sibling. It names uk_leads_feed and /uk-officer as different things, but never explains how it differs from uk_leads_lite, leaving one close sibling ambiguous.

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?

"Use this for..." plus the explicit routing of the recurring/webhook case to uk_leads_feed and reverse officer lookups to /uk-officer gives concrete alternatives with conditions. The gaps are that uk_leads_lite is never addressed and there are no stated exclusions (e.g., what happens for companies older than 7 days).

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