Request Add

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

With no annotations, the description carries the burden and does well: it declares this is a mutation that appends to an ordered queue and returns 'its id and its place in line', which tells the agent the effect and response shape. It leaves unstated whether duplicates are deduplicated, whether requests can be removed, or any rate limiting — minor gaps for a queue-append operation.

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?

Front-loaded with purpose, then a usage trigger, then a compact parameter glossary, then the return. Every sentence earns its place, though the parenthetical for venue ('credit and replies') is slightly opaque and the parameter block could be tighter.

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 4-parameter write tool with an output schema, the description covers purpose, trigger, all parameters and the sibling that consumes the queue. The main omissions are lifecycle details — whether entries can be edited/removed or what happens on duplicate requests — which an agent might want before logging repeated asks.

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%, and the description compensates fully by glossing all four parameters: who (viewer name as chat shows it), what (few-word request with concrete examples), venue (where they asked, used for credit/replies), note (anything the DJ should know). This adds meaning the bare schema strings could not convey, including why venue exists.

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?

States a specific verb and resource — put a viewer's song request into the DJ's play queue — which no sibling tool duplicates (request_vote, request_list, request_next all operate on the same queue but differently). The image of 'the queue the DJ plays from' distinguishes it from generic note-taking siblings like notes_write.

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?

Gives an explicit trigger: 'when chat asks for a song, a style or a change for the set', and names the downstream sibling request_next for reading the line. It does not mention the other request_* siblings (request_vote, request_list, request_credits) or when to refuse/reject a request, so routing guidance is clear but not exhaustive.

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