list_subscriptions

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

Beyond readOnlyHint and idempotentHint annotations, description reveals the tool is purely informational due to HTTP request/response architecture and returns an empty list if no subscription type exists, providing key behavioral context.

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?

Three concise sentences, front-loaded with core purpose, followed by crucial usage limitation and edge-case behavior. No redundant 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?

Covers purpose, constraints, and return behavior. No output schema exists, but description explains output is a list of subscription field names (with examples) and handles edge case (empty list). Could be slightly more explicit about output format, but adequate for the simple tool.

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?

Input schema already provides descriptions for both parameters (search: case-insensitive substring filter; limit: max number, default 200). Description does not add further parameter meaning, and schema coverage is 100%, so baseline score of 3 is appropriate.

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?

Clearly states the tool lists all root subscription fields with examples (messageAdded, onUserUpdate), distinguishing it from sibling tools like list_mutations and list_queries.

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?

Explicitly notes the server's HTTP limitation, states that subscriptions cannot be executed here, and directs users to use a websocket-based GraphQL client for consumption. Also explains behavior when schema has no subscription type.

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