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

Annotations already declare readOnlyHint=true, covering the safety profile. The description adds genuine behavioral value beyond that: 'ranked' signals a server-side default ordering behavior, and the field enumeration plus 'tracked for a project' scoping tells the agent what to expect in results. The only minor gap is no explicit statement about pagination, but annotations bear the core safety burden.

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?

Two sentences, zero filler. The first clause states the core purpose, followed immediately by the highest-value semantic detail ('ranked'). The filtering note is a natural second clause. Every word earns its place, and the key differentiator ('ranked') is front-loaded.

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 5-parameter tool with nested objects and no output schema, the description covers the essential semantics: what fields come back and how to filter. It doesn't explain sorting options or pagination, but those are discoverable from the schema's enum and structure. For this complexity level, the description is complete on the parts that aren't self-evident.

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 burden falls on the description, and it delivers: it explains the purpose of filters.ownership and filters.companyDomain, and previews the sortable/returned fields (queryCount, title, companyName). It doesn't mention cursor/limit/sorting, but those are structurally self-evident from the schema, so the description wisely spends its budget on the less-obvious ranking and filtering semantics.

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 names a specific verb ('List') and resource ('ranked pages tracked for a project'), and enumerates the exact fields returned (URL, title, company, query count, ownership). It immediately differentiates this from the many sibling list_* tools by the unique 'ranked pages' resource and the project scoping, so an agent can select it without opening the schema.

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?

The description states its filtering capabilities ('Filter by ownership or company domain') and defines its scope as project-tracked ranked pages, which cleanly distinguishes it from sibling list_* tools operating on other resources (keywords, competitors, opportunities). It doesn't explicitly name alternatives or exclusions, but the resource identity is clear enough that an agent wouldn't confuse it with, say, list_keywords.

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