get_graph_list

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

Beyond the annotations (readOnlyHint and openWorldHint), the description details specific behaviors: internal graphs are filtered out, graph URIs containing the database substring are ranked first, and it returns a CSV list. It also discloses the error response prefix, adding transparency about output format and failure modes.

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 front-loaded with purpose, then proceeds to usage constraints, ranking behavior, fallback logic, and return format. Each sentence adds value without redundancy. Though a bit long, the density of relevant information justifies its length.

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 tool with 4 parameters and a complex registry logic, the description covers all necessary context: required input, alternative inputs, ranking behavior, internal graph filtering, and error handling. The presence of an output schema is complemented by the description's explanation of CSV format and 'Error:' prefix, making the tool fully understandable.

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 already cover all parameters (100% coverage), but the description adds semantic depth: it explains the dual role of database (validation vs ranking), priority between endpoint_url and endpoint_name, and how include_system affects output. This goes beyond simple schema documentation and helps agents use parameters correctly.

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 the tool's purpose: 'Get a list of named graphs on a SPARQL endpoint.' It specifies the action (list), the resource (named graphs), and the context (SPARQL endpoint). It also distinguishes from siblings by highlighting endpoint discovery and filtering/ranking behavior, which is unique among the provided tools.

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 explicit usage guidance: 'ALWAYS pass database (required)' and explains when to use endpoint_url vs endpoint_name for unregistered databases, and how database value is used for ranking. It also warns about the 'Error:' prefix in return values, covering both usage conditions and error expectations.

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