clean_leads

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose the substantive behaviors: normalization of four field types, removal of invalid emails, and deduplication. However, it does not disclose the dedupe key (email? name+company?), whether input order is preserved, or whether it returns a new list versus mutating anything, which are exactly the details an agent needs to interpret output.

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?

A single well-formed sentence that front-loads the verb and the resource, then lists effects in a scannable colon-list. No filler, no repetition of the tool name.

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 and no annotations, so the description is the only source of truth, yet it never says what the return value looks like (cleaned leads plus a report of dropped items? just the cleaned list?) or how the 5000-item cap behaves. For a data-transforming tool with a nested payload, that leaves a meaningful gap.

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?

There is only one parameter, but schema description coverage is 0% and the parameter is a nested array of lead objects, so the description must do the semantic work. It names four of the five object fields (name, email, phone, website) but silently omits 'company', leaving an agent unsure whether company is preserved, passed through, or dropped. The mapping of described operations to fields is helpful but incomplete.

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 has a specific verb ('Clean') and resource ('a list of sales leads'), then enumerates the concrete operations: normalize names, emails, phones and websites, drop invalid emails, remove duplicates. That is far more informative than a restatement of the name. It does not, however, contrast itself with the sibling validate_email, so an agent must infer that this is the batch-level operation.

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 plural 'list of leads' signals a bulk operation, while validate_email suggests single-record validation, but the description never states when to choose one over the other or any preconditions. There are no explicit exclusions or escalation rules.

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