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

The description frames this as a pure 'List' read, but the annotations declare readOnlyHint=false and destructiveHint=true. Nothing in the text explains how a listing call could be destructive, what state it touches, or what auth/session conditions apply. The mismatch between the read framing and the destructive annotation is unresolved, so the description adds no behavioral context beyond the structured fields.

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?

One short sentence with no filler, so nothing is wasted, but it is front-loaded only with the title echo and contains no additional information. Brevity here reflects under-specification rather than disciplined concision.

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?

This is a complex wrapper tool with five required parameters including a session work_id, read_skills proof array, request_key and expected_catalog_version, plus pagination and an output schema. The description conveys none of this machinery, no pagination behavior, and no indication of what a plan record contains or how it is later used. An output schema exists, so return values need not be detailed, but the invocation context is left completely to 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?

Six parameters with only ~50% schema description coverage, and the description names none of them. 'Selected advertiser connection' loosely implies account_id but does not say so, and the pagination cursor 'after', the session 'work_id'/'request_key' keys, and the read_skills proof requirement are entirely unexplained in prose. The description does not compensate for the coverage gap.

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 sentence is a verbatim restatement of the tool title: 'List native lead form plans for the selected advertiser connection.' It names the verb and resource, but supplies nothing about what a 'lead form plan' is or how it differs from the nearby siblings native.genads_lead_forms, native.genads_lead_form_review, native.genads_lead_form_result and native.genads_save_lead_form_plan, which an agent must disambiguate by name alone.

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?

There is no when-to-use guidance, no statement of prerequisites, and no routing to alternatives. An agent cannot tell from this text whether to call this or native.genads_lead_forms / native.genads_lead_form_review, nor when saving a plan (native.genads_save_lead_form_plan) is required first. The only faint signal is the phrase 'selected advertiser connection'.

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