get_entities

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions that entities are 'real-world concepts' and gives examples (customers, transactions, ad campaigns), but doesn't describe what the tool actually returns - whether it's metadata, identifiers, full objects, or something else. It doesn't address pagination, rate limits, authentication requirements, error conditions, or what happens with invalid metrics. The behavioral expectations are largely undefined.

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 reasonably concise with clear sectioning using <instructions> and <parameters> tags. The first sentence directly states the tool's purpose, and the entity definition is relevant context. However, the entity examples could be more targeted to this specific tool rather than generic business concepts. The structure is good but could be more front-loaded with critical information.

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 1 parameter with 0% schema coverage, no annotations, and no output schema, the description is incomplete. It doesn't adequately explain what the tool returns, how entities relate to metrics, what format the response takes, or error handling. For a tool that presumably returns data based on metric inputs, the description leaves too many operational questions unanswered, especially considering the lack of structured metadata.

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 0%, so the description must compensate. It only states 'metrics: List of metric names' which repeats the parameter name without adding meaningful semantics. It doesn't explain what constitutes a valid metric name, where to find available metrics, whether there are constraints on the list size, or what happens if metrics don't exist. The description fails to provide the necessary parameter context that the schema lacks.

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 states 'Get the entities for specified metrics' which provides a basic verb+resource combination. However, it's vague about what 'entities' actually are in this context - while it defines entities generically as 'real-world concepts in a business', it doesn't specify what type of entities this particular tool returns or how they relate to the metrics. The description distinguishes from some siblings (like 'list_metrics' or 'query_metrics') but not clearly from others like 'get_dimensions' or 'get_all_models'.

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 provides no explicit guidance on when to use this tool versus alternatives. While it mentions that 'Analysis is often focused around specific entities', this is generic context rather than practical usage guidance. There's no mention of when to choose this tool over sibling tools like 'get_dimensions' or 'list_metrics', nor any prerequisites or constraints for its use.

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