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

The description goes beyond readOnlyHint by disclosing that it returns exactly the user's visibility, indicating that results are scoped by permissions. It also includes a security warning about CRM field values being untrusted, which is valuable behavioral context. However, it doesn't detail other behaviors like pagination limits beyond the schema, but the annotations already cover safety.

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 description is concise and front-loaded with the main purpose and visibility scope. It packs a lot of information in two sentences without being verbose. Could be slightly more structured, separating the security note, but overall efficient.

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?

Given the complexity (nested filters, 8 params) and lack of output schema, the description provides essential guidance on return shape ({items, nextCursor, totalCount}) and parameter usage. It doesn't explain all operators, but that's delegated to describe_object, which is reasonable. It covers security and visibility, making it complete enough for correct invocation.

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 schema coverage at 13%, the description compensates by explaining key parameters like filters (metadata-driven from describe_object), sortBy, cursor pagination, and limit cap of 50. It clarifies that filters use fieldKey/operator from describe_object, which is not evident from the raw schema. The nested filters schema is complex, and the description helps agents understand its origin and usage.

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 clearly states it lists records of one object type with the user's exact visibility, featuring a specific verb and resource. It distinguishes from siblings like get_record (single record) and search (cross-object) by emphasizing single object type and visibility scope.

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 explicitly mentions support for search, filters, sorting, and pagination, and notes the visibility constraint, providing clear context for when to use. However, it doesn't explicitly state when to use alternatives like search or get_record, so it's a bit short of a 5.

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