cases

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals pagination structure (outer vs nested), the specific page-size variables, and a workaround for a GreyMatter server-side error (omitting discoverExposure). This goes beyond the schema and provides actionable behavioral details, though it does not mention potential side effects or output shape beyond the nested connections.

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 dense but appropriately sized given 17 parameters. It front-loads the core purpose, then explains pagination, lists variables, shows an example, and ends with a caveat. Every sentence carries information, though the long example and variable enumeration make it somewhat heavy; still, it's well-structured and not wasteful.

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 high complexity (17 params), no annotations, and no output schema, the description is remarkably complete. It explains the nested structure, pagination semantics, provides a concrete example, and even includes a workaround for a known server issue. It lacks explicit response shape, but for a listing operation with this much nested detail, it covers the essential context an agent needs to invoke it correctly.

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?

The schema descriptions are generic types like 'GraphQL: String' and empty objects, providing no real semantics. The description compensates by explaining the role of key parameters: 'first3' bounds the outer list, 'first'/'first1'/'first2' page nested connections, and all variables are listed with an example showing how to use filters and ordering. This adds substantial meaning far beyond the schema.

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 opens with 'List cases (with nested activity/children/comments connections)' which clearly states the action (list), resource (cases), and scope (nested connections). The plural 'cases' combined with the sibling tool 'case' (singular) distinguishes it as the list operation versus a single-case fetch.

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 gives clear context on pagination: 'The OUTER list page size is `first3`... `first`/`first1`/`first2` page the nested connections.' It also provides an example and a note about using graphql_query for discoverExposure, offering an explicit alternative for that field. However, it does not explicitly state when to prefer this over other case-related tools or provide exclusions, but the context is clear enough.

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