call_endpoint

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

No annotations are provided, so the description carries full burden - and it does well: it discloses that GET reads are auto-paginated, that write operations execute live against the database (a significant side-effect disclosure), and that it validates against a catalog before calling. It falls just short of 5 because it doesn't explicitly note result size limits, rate limits, or what happens on validation failure, though the schema's pagination default of 1000 partially fills this gap.

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. Front-loaded with the primary purpose, then the payload structure. Every clause earns its place, covering validation, execution mode, pagination, and the prerequisite workflow without redundancy.

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 complex, generic dispatch tool (no output schema, nested objects, many free-form params), the description explains the overall execution model, safety difference between reads and writes, and the prerequisite (describe_endpoint). It's fairly complete given the inherent genericness of the tool. Slight gap: it doesn't describe error/response format or note limits, but given the tool is inherently generic across many endpoints, the description realistically cannot enumerate every behavior, so 4 is appropriate.

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 - and it partially does by explaining the flow of validation and pagination. However, the parameter-level semantics are mostly carried by the schema's own per-field descriptions (filters, paginate_results, body, etc.) which are detailed. The description adds value by explaining the GET-write behavioral distinction and the describe_endpoint prerequisite, but doesn't explain the filters wrapper or pagination fields - those are already in the schema, which does the heavy lifting for parameter meaning.

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?

Description states a specific verb+resource ('Call an AppFolio Database API endpoint and return its JSON response') and clearly outlines the execution flow (validates operationId, auto-paginates GET reads, executes live writes). It distinguishes from siblings by explicitly referencing describe_endpoint and list_endpoints as the setup tools, establishing a clear division of labor within the tool family.

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 explicit guidance on when to use this tool: 'Use describe_endpoint first to learn the exact params and body.' It also clarifies behavioral differences between GET (auto-paginated) and POST/PATCH/PUT/DELETE (live writes), helping the agent understand when live writes occur versus safe reads. This functional distinction is effectively an implied when-to-use/alternatives guideline given sibling tools are list/describe functions.

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