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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds genuine behavioral context about cost per request, empty results still charging, and the zero-cost terminal cursor call. That value is undercut by internally conflicting pricing claims ('one credit per successful request' versus 'completed lookups cost at least 10 Nexscope credits'), which could mislead an agent reasoning about spend.

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 same paragraph is duplicated three times, with an embedded 'Cosmos User Collections API View Pricing 1 credit per request' fragment pasted mid-text. The correct lead sentence is front-loaded, but the redundancy and boilerplate substantially dilute it.

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 two-parameter read tool with no output schema, the definition covers the essentials: public-only scope, credit cost, and the cursor/has_more pagination contract. It still omits what a collection record contains and repeats itself instead of expanding coverage, so it is adequate rather than complete.

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%, and both parameters are documented there, including the exact cursor semantics and the 'null' string trick. The description restates the cursor behavior already in the schema and adds nothing new about the handle format, so it does not exceed the baseline for fully documented parameters.

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 sentence gives a specific verb and resource: 'Get the public collections owned by a Cosmos user', with an explicit 'Public data only' scope qualifier. However, it never reconciles 'collections' with the tool name's 'clusters', and it does not distinguish this from siblings like social_cosmos_cluster or social_cosmos_user_posts.

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?

It gives usable invocation rules for pagination: keep the cursor unchanged, stop when has_more is false, and pass cursor=null to get a terminal empty page at zero cost. What it lacks is any statement of when to choose this over social_cosmos_cluster or social_cosmos_user_posts, so selection among the Cosmos siblings is left to inference.

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