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

Annotations only declare readOnly/non-destructive/closed-world; the description adds normalization behavior (E.164, registrable domain, transliteration), a five-level match taxonomy with the resulting decision semantics, access scoping ('only leads the caller may see'), and a non-obvious negative rule that *.business.site / prom.ua / instagram.com sub-sites are not the same domain.

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?

Front-loads the purpose and the pre-condition, then packs normalization and the tier ladder into a short paragraph with no filler. The tier enumeration is dense and telegraphic but every clause carries operational meaning.

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 9-parameter, no-output-schema tool, it covers matching logic, decision outcomes, and visibility scope, which is most of what an agent needs. It stops short of describing the response shape (candidate list/score fields implied by 'would_action') and the meaning/default of 'limit'.

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?

With 0% schema description coverage, the description carries the load well: it names every meaningful lookup key and explains how phone, domain/website_url, and company values are normalized before comparison. Gaps remain — 'limit' is never mentioned, and the phone vs. phones (single vs. up to 10 candidates) distinction is not clarified.

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?

Opens with a specific verb+resource+decision: 'Check whether a company is already among the caller's CRM leads BEFORE creating it.' It also enumerates the identity keys accepted and the match tiers, so an agent knows exactly what question the tool answers, distinct from creation or import siblings.

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?

Explicitly states the temporal condition ('BEFORE creating it') and prescribes downstream action per outcome: levels 1–4 → would_action 'update', level 5 → 'conflict' (a human decides). It also gives a hard input precondition: 'Provide at least one of: phone | phones | email | domain | website_url | edrpou | company.'

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