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

Well beyond the annotations, the description discloses pricing tiers, key requirements, the 25/1000 record ceilings, the shape of the response ('findings per record with proposed fixes') and confirms no side effects ('Nothing is stored or changed'), which is valuable given there is no output schema. It stops short of saying what happens when the record limit is exceeded (error vs. truncation) or how findings are prioritized.

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 definition is compact and front-loaded with the most decision-relevant fact (FREE, with limits), followed by the check inventory and the side-effect guarantee. The mid-sentence ellipsis list is dense but each clause carries real information; no sentence is filler.

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 four-parameter tool with no output schema, the description covers cost, quotas, return shape and mutation safety, which is most of what an agent needs. Gaps remain around behavior at the quota boundary and the dangling `options`/pricing reference, which an agent cannot resolve from either the description or the schema.

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 every parameter including the `ai` flag, `language`, and `categories` is already documented in structured fields; the tool description adds no parameter-level detail of its own. It also does not clarify the key requirement the schema's `ai` text references, nor reconcile the mention of an `options` object that does not exist in the schema (additionalProperties: false).

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 and resource ('check contact records for errors') and enumerates the concrete check classes (email typos, role mailboxes, duplicates, phone/country mismatch, LinkedIn status text in names, placeholders), which makes the tool unmistakably a bulk record validator. It never names the overlapping sibling verify_email, so an agent must infer the boundary between single-address verification and full-record checking.

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?

Usage is only implied: the free-tier thresholds ('up to 25 records without a key, 1000 with one') and the note that `ai` is PAID tell the agent something about cost-driven selection, but there is no explicit 'use this when…' or 'use X instead' statement. Nothing tells the agent when to prefer enrich_records or verify_email over this tool.

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