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

Annotations only declare readOnlyHint and destructiveHint, so the description adds substantial behavioral value: the categoryAttributeWarmup pending:true provisional-count caveat, the ruleEnabled=false effective-source nuance, the currency double-conversion risk, the 'default is not a decision' trust warning, and the step-vs-override precedence rule. The mention of writing an override refers to map_ad_attribute's behavior, not this tool's, so it does not contradict readOnlyHint.

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-loaded with purpose and nearly every clause carries unique, non-redundant information, so the length is largely justified by complexity. However, the definition is one dense unbroken paragraph with two text-merge artifacts — 'ad_id is from Each row also says WHERE its value comes from' and the orphaned 'list_ads.' fragment — that break the reading flow and obscure 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?

With no output schema and high complexity (20+ return fields, provisional-state semantics, currency conversion rules), the description carries the full burden and nearly succeeds: it enumerates the return structure, defines the valueSource enum, explains requiredUnmappedCount/unresolvedCodes, and flags the warmup incompleteness. The garbled ad_id provenance sentence and the mid-paragraph burial of the critical warmup warning slightly reduce practical completeness.

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 only 33% schema description coverage (only only_unresolved documented), the description compensates for all three parameters: ad_id is sourced from list_ads, project_id's optionality plus the project_id_required branch to list_projects, and only_unresolved:true filters to required-unmapped rows. This is full semantic compensation 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 opening clause 'List an ad's OUTPUT attributes and how each is currently sourced' names a specific verb, resource, and scope, and the parenthetical 'the tool for SOLVING THE ATTRIBUTE FORM' brands its distinct role among siblings like get_marketplace_attributes, get_attribute_options, and map_ad_attribute. The read-vs-write nature is unambiguous from 'List' and 'Returns'.

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?

Provides explicit route guidance: fill attributes via map_ad_attribute, change step-driven fields via configure_ad_step with the warning that mapping writes a permanent override, obtain ad_id from list_ads, call list_projects when project_id_required, and poll ad_status during categoryAttributeWarmup. This is exemplary when/when-not coverage against a large sibling set.

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